{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "vnlTnQFHyjcG"
   },
   "source": [
    "## Logistic Regression (Binary Classification)\n",
    "\n",
    "### Business Problem Definition\n",
    "The business problem revolves around **predicting the likelihood of order cancellations** for a product fulfillment company based on historical order data. This prediction helps the company:\n",
    "\n",
    "- Proactively address potential cancellations,\n",
    "- Optimize operations, and\n",
    "- Improve customer satisfaction.\n",
    "\n",
    "By identifying high-risk orders early, the business can take preventive actions, such as offering incentives or expedited shipping, to reduce the likelihood of cancellations.\n",
    "\n",
    "This is a binary classification problem where the target variable is the Order_Cancelled column.\n",
    "\n",
    "The model needs to classify whether an order will be cancelled based on features like the delivery time, order value, region, and other order-related factors.\n",
    "\n",
    "---\n",
    "\n",
    "### Dataset Description\n",
    "\n",
    "#### Target Variable:\n",
    "- **Order_Cancelled** (binary categorical):  \n",
    "  The binary target variable indicating whether an order was cancelled (`1`) or not cancelled (`0`).  \n",
    "  This is the variable that the classification model will predict based on the other feature columns.\n",
    "\n",
    "---\n",
    "\n",
    "#### Feature Columns:\n",
    "\n",
    "Explanation of Attributes/Target Variable:\n",
    "\n",
    "\\\n",
    "Each row represents an `order placed by the customer` while columms represent the varied specifics of that order.\n",
    "\n",
    "\\\n",
    "\n",
    "- `Days_to_Delivery` (numeric):  \n",
    "  The number of days it takes for the order to be delivered, generated based on a normal distribution with a mean of 5 days and a standard deviation of 2 days.\n",
    "\n",
    "- `Num_Items_Ordered` (numeric):  \n",
    "  The total number of items in the order, represented as an integer between 1 and 20, reflecting the quantity of products ordered.\n",
    "\n",
    "- `Order_Value` (numeric):  \n",
    "  The total value of the order in USD. It is generated from a normal distribution centered around $500, with a standard deviation of $100.\n",
    "\n",
    "- `Discount_Rate` (numeric):  \n",
    "  The discount rate applied to the order, represented as a value between 0 and 0.5, indicating various discounts offered during sales.\n",
    "\n",
    "- `Num_Previous_Orders` (numeric):  \n",
    "  The number of previous orders placed by the customer. It is an integer between 0 and 10.\n",
    "\n",
    "- `Delivery_Time_Variation` (numeric):  \n",
    "  The variation between the estimated and actual delivery time, measured in days, with values ranging from 0 to 3 days.\n",
    "\n",
    "- `Region` (categorical):  \n",
    "  The geographic region of the customer. Possible values:\n",
    "  - North America\n",
    "  - EMEA (Europe, Middle East, Africa)\n",
    "  - APAC (Asia-Pacific)\n",
    "  - LATAM (Latin America)\n",
    "\n",
    "- `Product_Category` (categorical)\n",
    "  The category of the product ordered. Possible values:\n",
    "  - Cloud\n",
    "  - On-premise\n",
    "  - SaaS (Software as a Service)\n",
    "  - Hardware\n",
    "\n",
    "- `Order_Priority` (categorical):  \n",
    "  The urgency level of the order. Possible values:\n",
    "  - Low\n",
    "  - Medium\n",
    "  - High\n",
    "\n",
    "- `Payment_Method` (categorical):  \n",
    "  The method used for payment in the order. Possible values include:\n",
    "  - Credit Card\n",
    "  - Bank Transfer\n",
    "  - PayPal\n",
    "  - Bitcoin\n",
    "\n",
    "- `Correlated_Order_Value` (numeric):  \n",
    "  Represents an alternative estimation of the total order value, calculated by factoring in **historical customer spending behavior** and **product pricing trends**.It incorporates additional business insights such as customer loyalty and purchasing history.\n",
    "\n",
    "\n",
    "- `Order_Cancelled (Target):` This is the target column indicating whether the order was cancelled or not. Values are \"Cancelled\" or \"Not-Cancelled\".\n",
    "\n",
    "---\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6IUzkBonZONu"
   },
   "source": [
    "### Comprehensive Data Science Project Workflow: From Business Understanding to Model Monitoring:\n",
    "\n",
    "1. `Business Understanding` (Define project goals and objectives.)\n",
    "\n",
    "2. `Data Requirement` (Identify necessary data for analysis)\n",
    "\n",
    "3. `Data Collection` (Data gathering from different sources with varied tools and technologies)\n",
    "\n",
    "4. `Data Preparation` (EDA/Data Preparation/Data Cleaning/Data Munging)\n",
    "\n",
    "5. `Data Modeling` ( Clean Data + Algorithms = Model)\n",
    "\n",
    "6. `Model Evaluation`  (Test Model perf)\n",
    "\n",
    "7. `Model Tuning`(Optimize model hyperparameters)\n",
    "\n",
    "8. `Model Deployment`(Deploy model for real-time use)\n",
    "\n",
    "9. `Monitoring`(Track model performance over time)\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ZhWWiqkiZO6a"
   },
   "source": [
    "### EDA/ Data Preparation/Data Cleaning Steps:\n",
    "\n",
    "1. `Removing Duplicate data`\n",
    "2. `Missing Value Treatment`\n",
    "3. `Outlier Treatment`\n",
    "4. `Categorical to Numerical Conversion`\n",
    "5. `Numerical to Categorical Conversion`\n",
    "6. `Feature Scaling`\n",
    "7. `Feature Transformation`\n",
    "8. `Feature selection`\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "collapsed": true,
    "id": "QHaf7cF-0D2x",
    "jupyter": {
     "outputs_hidden": true
    },
    "outputId": "acddc04e-42cd-4fe7-f61d-9a43c50a5bf2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting shap\n",
      "  Downloading shap-0.46.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (24 kB)\n",
      "Collecting statsmodels\n",
      "  Downloading statsmodels-0.14.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (9.2 kB)\n",
      "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from shap) (1.26.4)\n",
      "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from shap) (1.13.1)\n",
      "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from shap) (1.5.2)\n",
      "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from shap) (2.1.4)\n",
      "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.10/dist-packages (from shap) (4.66.5)\n",
      "Requirement already satisfied: packaging>20.9 in /usr/local/lib/python3.10/dist-packages (from shap) (24.1)\n",
      "Collecting slicer==0.0.8 (from shap)\n",
      "  Downloading slicer-0.0.8-py3-none-any.whl.metadata (4.0 kB)\n",
      "Requirement already satisfied: numba in /usr/local/lib/python3.10/dist-packages (from shap) (0.60.0)\n",
      "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.10/dist-packages (from shap) (3.0.0)\n",
      "Collecting patsy>=0.5.6 (from statsmodels)\n",
      "  Downloading patsy-0.5.6-py2.py3-none-any.whl.metadata (3.5 kB)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2024.2)\n",
      "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2024.1)\n",
      "Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from patsy>=0.5.6->statsmodels) (1.16.0)\n",
      "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba->shap) (0.43.0)\n",
      "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (1.4.2)\n",
      "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (3.5.0)\n",
      "Downloading shap-0.46.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (540 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m540.1/540.1 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading slicer-0.0.8-py3-none-any.whl (15 kB)\n",
      "Downloading statsmodels-0.14.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.8 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.8/10.8 MB\u001b[0m \u001b[31m63.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading patsy-0.5.6-py2.py3-none-any.whl (233 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m233.9/233.9 kB\u001b[0m \u001b[31m15.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hInstalling collected packages: slicer, patsy, statsmodels, shap\n",
      "Successfully installed patsy-0.5.6 shap-0.46.0 slicer-0.0.8 statsmodels-0.14.3\n"
     ]
    }
   ],
   "source": [
    "%pip install shap statsmodels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 264
    },
    "id": "MlaoGK9Kyl8e",
    "outputId": "03110e55-0c50-44bb-f101-0ff3a09a8896"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"df\",\n  \"rows\": 4000,\n  \"fields\": [\n    {\n      \"column\": \"Days_to_Delivery\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.994307840004563,\n        \"min\": -1.4825346801381452,\n        \"max\": 12.852475412872652,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          4.588281138239319,\n          6.848540279075659,\n          4.583766285454921\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Items_Ordered\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5,\n        \"min\": 1,\n        \"max\": 19,\n        \"num_unique_values\": 19,\n        \"samples\": [\n          16,\n          7,\n          12\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 100.2130314677825,\n        \"min\": 130.3378094310662,\n        \"max\": 841.4187025980059,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          534.0622328238003,\n          732.0218220267479,\n          485.5762040062945\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Discount_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.14292836009448692,\n        \"min\": 8.775792896165147e-05,\n        \"max\": 0.4999463333525246,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.131760721241866,\n          0.3155826053495354,\n          0.31135019811647\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Previous_Orders\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2,\n        \"min\": 0,\n        \"max\": 9,\n        \"num_unique_values\": 10,\n        \"samples\": [\n          0,\n          2,\n          3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Delivery_Time_Variation\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8716236709628011,\n        \"min\": 0.0006041944029312,\n        \"max\": 2.99946649608437,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.7979158312926778,\n          2.8416834043829686,\n          2.144395823199287\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"North America\",\n          \"EMEA\",\n          \"APAC\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Product_Category\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 61,\n        \"samples\": [\n          \"Oracle SOA Suite\",\n          \"Oracle Education Cloud\",\n          \"Oracle Blockchain Platform\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"Low\",\n          \"Medium\",\n          \"High\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"PayPal\",\n          \"Bitcoin\",\n          \"Credit Card\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Cancelled\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"Cancelled\",\n          \"Not-Cancelled\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Correlated_Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 95.35982445380614,\n        \"min\": 120.4281477270148,\n        \"max\": 791.0946013871961,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          504.113753506419,\n          699.9149033564593\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "df"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-b99a8d24-8e66-488d-8776-34cd262282b9\" 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>Days_to_Delivery</th>\n",
       "      <th>Num_Items_Ordered</th>\n",
       "      <th>Order_Value</th>\n",
       "      <th>Discount_Rate</th>\n",
       "      <th>Num_Previous_Orders</th>\n",
       "      <th>Delivery_Time_Variation</th>\n",
       "      <th>Region</th>\n",
       "      <th>Product_Category</th>\n",
       "      <th>Order_Priority</th>\n",
       "      <th>Payment_Method</th>\n",
       "      <th>Order_Cancelled</th>\n",
       "      <th>Correlated_Order_Value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.176246</td>\n",
       "      <td>16</td>\n",
       "      <td>532.685241</td>\n",
       "      <td>0.100711</td>\n",
       "      <td>8</td>\n",
       "      <td>1.601869</td>\n",
       "      <td>APAC</td>\n",
       "      <td>Oracle SOA Suite</td>\n",
       "      <td>Low</td>\n",
       "      <td>Credit Card</td>\n",
       "      <td>Not-Cancelled</td>\n",
       "      <td>505.651649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.573086</td>\n",
       "      <td>8</td>\n",
       "      <td>367.854514</td>\n",
       "      <td>0.117976</td>\n",
       "      <td>2</td>\n",
       "      <td>2.425666</td>\n",
       "      <td>North America</td>\n",
       "      <td>Oracle VM VirtualBox</td>\n",
       "      <td>Medium</td>\n",
       "      <td>PayPal</td>\n",
       "      <td>Not-Cancelled</td>\n",
       "      <td>348.849923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.096170</td>\n",
       "      <td>13</td>\n",
       "      <td>640.514439</td>\n",
       "      <td>0.292261</td>\n",
       "      <td>9</td>\n",
       "      <td>2.622599</td>\n",
       "      <td>APAC</td>\n",
       "      <td>Oracle Transportation Management</td>\n",
       "      <td>Medium</td>\n",
       "      <td>PayPal</td>\n",
       "      <td>Not-Cancelled</td>\n",
       "      <td>611.311508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.327226</td>\n",
       "      <td>10</td>\n",
       "      <td>434.579153</td>\n",
       "      <td>0.243082</td>\n",
       "      <td>8</td>\n",
       "      <td>0.472247</td>\n",
       "      <td>LATAM</td>\n",
       "      <td>Oracle Cloud Applications</td>\n",
       "      <td>Low</td>\n",
       "      <td>PayPal</td>\n",
       "      <td>Cancelled</td>\n",
       "      <td>412.479846</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-b99a8d24-8e66-488d-8776-34cd262282b9')\"\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-b99a8d24-8e66-488d-8776-34cd262282b9 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-b99a8d24-8e66-488d-8776-34cd262282b9');\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-857d2d93-c2a7-4655-8e6c-5f9a3c6a5d20\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-857d2d93-c2a7-4655-8e6c-5f9a3c6a5d20')\"\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-857d2d93-c2a7-4655-8e6c-5f9a3c6a5d20 button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   Days_to_Delivery  Num_Items_Ordered  Order_Value  Discount_Rate  \\\n",
       "0          4.176246                 16   532.685241       0.100711   \n",
       "1          4.573086                  8   367.854514       0.117976   \n",
       "2          5.096170                 13   640.514439       0.292261   \n",
       "3          4.327226                 10   434.579153       0.243082   \n",
       "\n",
       "   Num_Previous_Orders  Delivery_Time_Variation         Region  \\\n",
       "0                    8                 1.601869           APAC   \n",
       "1                    2                 2.425666  North America   \n",
       "2                    9                 2.622599           APAC   \n",
       "3                    8                 0.472247          LATAM   \n",
       "\n",
       "                   Product_Category Order_Priority Payment_Method  \\\n",
       "0                  Oracle SOA Suite            Low    Credit Card   \n",
       "1              Oracle VM VirtualBox         Medium         PayPal   \n",
       "2  Oracle Transportation Management         Medium         PayPal   \n",
       "3         Oracle Cloud Applications            Low         PayPal   \n",
       "\n",
       "  Order_Cancelled  Correlated_Order_Value  \n",
       "0   Not-Cancelled              505.651649  \n",
       "1   Not-Cancelled              348.849923  \n",
       "2   Not-Cancelled              611.311508  \n",
       "3       Cancelled              412.479846  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Load the dataset from the uploaded file\n",
    "file_path = 'order_mgmt_binary_class_high_cardinality.csv'\n",
    "\n",
    "# Read the dataset\n",
    "df = pd.read_csv(file_path)\n",
    "\n",
    "# Strip blank spaces from column names\n",
    "df.columns = df.columns.str.strip()\n",
    "\n",
    "# Display the first few rows and the column names\n",
    "df.head(4)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "_CT6aQHvymJv",
    "outputId": "aa6ae7bd-b079-44ca-db20-019de09fdb81"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Days_to_Delivery', 'Num_Items_Ordered', 'Order_Value', 'Discount_Rate',\n",
       "       'Num_Previous_Orders', 'Delivery_Time_Variation', 'Region',\n",
       "       'Product_Category', 'Order_Priority', 'Payment_Method',\n",
       "       'Order_Cancelled', 'Correlated_Order_Value'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 460
    },
    "id": "sPiJf67dymT4",
    "outputId": "d81782a5-2ac8-4f58-fe9e-a04befc62aca"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Days_to_Delivery</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Num_Items_Ordered</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Order_Value</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Discount_Rate</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Num_Previous_Orders</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Delivery_Time_Variation</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Region</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Product_Category</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Order_Priority</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Payment_Method</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Order_Cancelled</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Correlated_Order_Value</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> int64</label>"
      ],
      "text/plain": [
       "Days_to_Delivery           0\n",
       "Num_Items_Ordered          0\n",
       "Order_Value                0\n",
       "Discount_Rate              0\n",
       "Num_Previous_Orders        0\n",
       "Delivery_Time_Variation    0\n",
       "Region                     0\n",
       "Product_Category           0\n",
       "Order_Priority             0\n",
       "Payment_Method             0\n",
       "Order_Cancelled            0\n",
       "Correlated_Order_Value     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.impute import SimpleImputer\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# Replace '?' , 'NULL', 'NA', 'NaN' with np.nan for consistent missing value handling\n",
    "df.replace(['?', 'NULL', 'NA', 'NaN'], np.nan, inplace=True)\n",
    "\n",
    "# Separate numeric and categorical columns\n",
    "numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns\n",
    "categorical_columns = df.select_dtypes(include=['object']).columns\n",
    "\n",
    "# Define imputers for numeric (median) and categorical (most frequent) columns\n",
    "numeric_imputer = SimpleImputer(strategy='median')\n",
    "categorical_imputer = SimpleImputer(strategy='most_frequent')\n",
    "\n",
    "# Apply imputation separately\n",
    "df[numeric_columns] = numeric_imputer.fit_transform(df[numeric_columns])\n",
    "df[categorical_columns] = categorical_imputer.fit_transform(df[categorical_columns])\n",
    "\n",
    "# Check for any remaining missing values after imputation\n",
    "missing_values_after_imputation = df.isnull().sum()\n",
    "missing_values_after_imputation\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "n5suqM1Tr18H"
   },
   "outputs": [],
   "source": [
    "# Display the class-wise distributions\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 852
    },
    "id": "etoRoya5sK3g",
    "outputId": "86b2c335-2810-4ca6-a61a-8f043b5663c4"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x800 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Correlation Plot for Numeric Features\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt # Import the matplotlib.pyplot module\n",
    "\n",
    "# Compute the correlation matrix\n",
    "X = df[numeric_columns]\n",
    "correlation_matrix = X.corr()\n",
    "\n",
    "# Plot the heatmap\n",
    "plt.figure(figsize=(10, 8))\n",
    "sns.heatmap(correlation_matrix, annot=True, cmap=\"coolwarm\", fmt='.2f')\n",
    "plt.title('Correlation Heatmap of Numeric Features')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bhcP0xf3C0aQ"
   },
   "source": [
    "### Categorical column encoding using target and dummy encodings:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 243
    },
    "id": "V1SuAyfQymWD",
    "outputId": "7236c432-3c00-49fd-8cf7-48099b7f05bf"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"dataCleaned\",\n  \"rows\": 4000,\n  \"fields\": [\n    {\n      \"column\": \"Days_to_Delivery\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.994307840004563,\n        \"min\": -1.4825346801381452,\n        \"max\": 12.852475412872652,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          4.588281138239319,\n          6.848540279075659,\n          4.583766285454921\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Items_Ordered\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5.5100269542679365,\n        \"min\": 1.0,\n        \"max\": 19.0,\n        \"num_unique_values\": 19,\n        \"samples\": [\n          16.0,\n          7.0,\n          12.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 100.2130314677825,\n        \"min\": 130.3378094310662,\n        \"max\": 841.4187025980059,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          534.0622328238003,\n          732.0218220267479,\n          485.5762040062945\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Discount_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.14292836009448692,\n        \"min\": 8.775792896165147e-05,\n        \"max\": 0.4999463333525246,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.131760721241866,\n          0.3155826053495354,\n          0.31135019811647\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Previous_Orders\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.836039089457201,\n        \"min\": 0.0,\n        \"max\": 9.0,\n        \"num_unique_values\": 10,\n        \"samples\": [\n          0.0,\n          2.0,\n          3.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Delivery_Time_Variation\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8716236709628011,\n        \"min\": 0.0006041944029312,\n        \"max\": 2.99946649608437,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.7979158312926778,\n          2.8416834043829686,\n          2.144395823199287\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Product_Category\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.07073999886887665,\n        \"min\": 0.29508196721311475,\n        \"max\": 0.6615384615384615,\n        \"num_unique_values\": 56,\n        \"samples\": [\n          0.4470588235294118,\n          0.45901639344262296,\n          0.5079365079365079\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Cancelled\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1,\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Correlated_Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 95.35982445380614,\n        \"min\": 120.4281477270148,\n        \"max\": 791.0946013871961,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          504.113753506419,\n          699.9149033564593\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_EMEA\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_LATAM\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_North America\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Low\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Medium\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Bitcoin\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Credit Card\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_PayPal\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "dataCleaned"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-08a97103-c3ad-43b2-81bf-d5d43d577c10\" 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>Days_to_Delivery</th>\n",
       "      <th>Num_Items_Ordered</th>\n",
       "      <th>Order_Value</th>\n",
       "      <th>Discount_Rate</th>\n",
       "      <th>Num_Previous_Orders</th>\n",
       "      <th>Delivery_Time_Variation</th>\n",
       "      <th>Product_Category</th>\n",
       "      <th>Order_Cancelled</th>\n",
       "      <th>Correlated_Order_Value</th>\n",
       "      <th>Region_EMEA</th>\n",
       "      <th>Region_LATAM</th>\n",
       "      <th>Region_North America</th>\n",
       "      <th>Order_Priority_Low</th>\n",
       "      <th>Order_Priority_Medium</th>\n",
       "      <th>Payment_Method_Bitcoin</th>\n",
       "      <th>Payment_Method_Credit Card</th>\n",
       "      <th>Payment_Method_PayPal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.176246</td>\n",
       "      <td>16.0</td>\n",
       "      <td>532.685241</td>\n",
       "      <td>0.100711</td>\n",
       "      <td>8.0</td>\n",
       "      <td>1.601869</td>\n",
       "      <td>0.447059</td>\n",
       "      <td>0</td>\n",
       "      <td>505.651649</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.573086</td>\n",
       "      <td>8.0</td>\n",
       "      <td>367.854514</td>\n",
       "      <td>0.117976</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.425666</td>\n",
       "      <td>0.592105</td>\n",
       "      <td>0</td>\n",
       "      <td>348.849923</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.096170</td>\n",
       "      <td>13.0</td>\n",
       "      <td>640.514439</td>\n",
       "      <td>0.292261</td>\n",
       "      <td>9.0</td>\n",
       "      <td>2.622599</td>\n",
       "      <td>0.563636</td>\n",
       "      <td>0</td>\n",
       "      <td>611.311508</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.327226</td>\n",
       "      <td>10.0</td>\n",
       "      <td>434.579153</td>\n",
       "      <td>0.243082</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0.472247</td>\n",
       "      <td>0.545455</td>\n",
       "      <td>1</td>\n",
       "      <td>412.479846</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9.823353</td>\n",
       "      <td>1.0</td>\n",
       "      <td>439.779464</td>\n",
       "      <td>0.123217</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.805729</td>\n",
       "      <td>0.426230</td>\n",
       "      <td>0</td>\n",
       "      <td>418.039032</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</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-08a97103-c3ad-43b2-81bf-d5d43d577c10')\"\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-08a97103-c3ad-43b2-81bf-d5d43d577c10 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-08a97103-c3ad-43b2-81bf-d5d43d577c10');\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-e3fa4a9f-7d59-469c-a6e1-8be044e01035\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-e3fa4a9f-7d59-469c-a6e1-8be044e01035')\"\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-e3fa4a9f-7d59-469c-a6e1-8be044e01035 button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   Days_to_Delivery  Num_Items_Ordered  Order_Value  Discount_Rate  \\\n",
       "0          4.176246               16.0   532.685241       0.100711   \n",
       "1          4.573086                8.0   367.854514       0.117976   \n",
       "2          5.096170               13.0   640.514439       0.292261   \n",
       "3          4.327226               10.0   434.579153       0.243082   \n",
       "4          9.823353                1.0   439.779464       0.123217   \n",
       "\n",
       "   Num_Previous_Orders  Delivery_Time_Variation  Product_Category  \\\n",
       "0                  8.0                 1.601869          0.447059   \n",
       "1                  2.0                 2.425666          0.592105   \n",
       "2                  9.0                 2.622599          0.563636   \n",
       "3                  8.0                 0.472247          0.545455   \n",
       "4                  2.0                 0.805729          0.426230   \n",
       "\n",
       "   Order_Cancelled  Correlated_Order_Value  Region_EMEA  Region_LATAM  \\\n",
       "0                0              505.651649        False         False   \n",
       "1                0              348.849923        False         False   \n",
       "2                0              611.311508        False         False   \n",
       "3                1              412.479846        False          True   \n",
       "4                0              418.039032         True         False   \n",
       "\n",
       "   Region_North America  Order_Priority_Low  Order_Priority_Medium  \\\n",
       "0                 False                True                  False   \n",
       "1                  True               False                   True   \n",
       "2                 False               False                   True   \n",
       "3                 False                True                  False   \n",
       "4                 False               False                   True   \n",
       "\n",
       "   Payment_Method_Bitcoin  Payment_Method_Credit Card  Payment_Method_PayPal  \n",
       "0                   False                        True                  False  \n",
       "1                   False                       False                   True  \n",
       "2                   False                       False                   True  \n",
       "3                   False                       False                   True  \n",
       "4                   False                       False                  False  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Identify categorical columns\n",
    "categorical_cols = ['Region', 'Order_Priority', 'Payment_Method', 'Product_Category']\n",
    "non_product_category_cols = [col for col in categorical_cols if col != 'Product_Category']\n",
    "\n",
    "# 'Not-Cancelled' is 0 and 'Cancelled' is 1\n",
    "df['Order_Cancelled'] = df['Order_Cancelled'].map({'Not-Cancelled': 0, 'Cancelled': 1})\n",
    "\n",
    "# Manual target encoding for 'Product_Category'\n",
    "# Calculate the mean 'Order_Cancelled' for each category\n",
    "product_category_means = df.groupby('Product_Category')['Order_Cancelled'].mean()\n",
    "\n",
    "# Replace 'Product_Category' values with the corresponding mean\n",
    "df['Product_Category'] = df['Product_Category'].map(product_category_means)\n",
    "\n",
    "# Dummy encoding for other categorical columns\n",
    "df_encoded = pd.get_dummies(df, columns=non_product_category_cols, drop_first=True)\n",
    "\n",
    "# Store the resulting dataframe in a variable called 'dataCleaned'\n",
    "dataCleaned = df_encoded\n",
    "\n",
    "# Show the first few rows of the cleaned data\n",
    "dataCleaned.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 149
    },
    "id": "pp-0ldpKymYd",
    "outputId": "3d22dcc1-e46a-4b9b-b2d1-56884ed3798a"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"X\",\n  \"rows\": 4000,\n  \"fields\": [\n    {\n      \"column\": \"Days_to_Delivery\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.994307840004563,\n        \"min\": -1.4825346801381452,\n        \"max\": 12.852475412872652,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          4.588281138239319,\n          6.848540279075659,\n          4.583766285454921\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Items_Ordered\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5.5100269542679365,\n        \"min\": 1.0,\n        \"max\": 19.0,\n        \"num_unique_values\": 19,\n        \"samples\": [\n          16.0,\n          7.0,\n          12.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 100.2130314677825,\n        \"min\": 130.3378094310662,\n        \"max\": 841.4187025980059,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          534.0622328238003,\n          732.0218220267479,\n          485.5762040062945\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Discount_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.14292836009448692,\n        \"min\": 8.775792896165147e-05,\n        \"max\": 0.4999463333525246,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.131760721241866,\n          0.3155826053495354,\n          0.31135019811647\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Previous_Orders\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.836039089457201,\n        \"min\": 0.0,\n        \"max\": 9.0,\n        \"num_unique_values\": 10,\n        \"samples\": [\n          0.0,\n          2.0,\n          3.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Delivery_Time_Variation\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8716236709628011,\n        \"min\": 0.0006041944029312,\n        \"max\": 2.99946649608437,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.7979158312926778,\n          2.8416834043829686,\n          2.144395823199287\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Product_Category\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.07073999886887665,\n        \"min\": 0.29508196721311475,\n        \"max\": 0.6615384615384615,\n        \"num_unique_values\": 56,\n        \"samples\": [\n          0.4470588235294118,\n          0.45901639344262296,\n          0.5079365079365079\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Correlated_Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 95.35982445380614,\n        \"min\": 120.4281477270148,\n        \"max\": 791.0946013871961,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          504.113753506419,\n          699.9149033564593,\n          457.5634439009601\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_EMEA\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_LATAM\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_North America\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Low\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Medium\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Bitcoin\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Credit Card\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_PayPal\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "X"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-c1bd2871-deec-4700-8634-dba0855dcff9\" 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>Days_to_Delivery</th>\n",
       "      <th>Num_Items_Ordered</th>\n",
       "      <th>Order_Value</th>\n",
       "      <th>Discount_Rate</th>\n",
       "      <th>Num_Previous_Orders</th>\n",
       "      <th>Delivery_Time_Variation</th>\n",
       "      <th>Product_Category</th>\n",
       "      <th>Correlated_Order_Value</th>\n",
       "      <th>Region_EMEA</th>\n",
       "      <th>Region_LATAM</th>\n",
       "      <th>Region_North America</th>\n",
       "      <th>Order_Priority_Low</th>\n",
       "      <th>Order_Priority_Medium</th>\n",
       "      <th>Payment_Method_Bitcoin</th>\n",
       "      <th>Payment_Method_Credit Card</th>\n",
       "      <th>Payment_Method_PayPal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.176246</td>\n",
       "      <td>16.0</td>\n",
       "      <td>532.685241</td>\n",
       "      <td>0.100711</td>\n",
       "      <td>8.0</td>\n",
       "      <td>1.601869</td>\n",
       "      <td>0.447059</td>\n",
       "      <td>505.651649</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.573086</td>\n",
       "      <td>8.0</td>\n",
       "      <td>367.854514</td>\n",
       "      <td>0.117976</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.425666</td>\n",
       "      <td>0.592105</td>\n",
       "      <td>348.849923</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</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-c1bd2871-deec-4700-8634-dba0855dcff9')\"\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-c1bd2871-deec-4700-8634-dba0855dcff9 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-c1bd2871-deec-4700-8634-dba0855dcff9');\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-0e4b7d0d-ed46-4b98-86ba-0b277d9cab35\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-0e4b7d0d-ed46-4b98-86ba-0b277d9cab35')\"\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-0e4b7d0d-ed46-4b98-86ba-0b277d9cab35 button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   Days_to_Delivery  Num_Items_Ordered  Order_Value  Discount_Rate  \\\n",
       "0          4.176246               16.0   532.685241       0.100711   \n",
       "1          4.573086                8.0   367.854514       0.117976   \n",
       "\n",
       "   Num_Previous_Orders  Delivery_Time_Variation  Product_Category  \\\n",
       "0                  8.0                 1.601869          0.447059   \n",
       "1                  2.0                 2.425666          0.592105   \n",
       "\n",
       "   Correlated_Order_Value  Region_EMEA  Region_LATAM  Region_North America  \\\n",
       "0              505.651649        False         False                 False   \n",
       "1              348.849923        False         False                  True   \n",
       "\n",
       "   Order_Priority_Low  Order_Priority_Medium  Payment_Method_Bitcoin  \\\n",
       "0                True                  False                   False   \n",
       "1               False                   True                   False   \n",
       "\n",
       "   Payment_Method_Credit Card  Payment_Method_PayPal  \n",
       "0                        True                  False  \n",
       "1                       False                   True  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Prepare data for logistic regression\n",
    "X = dataCleaned.drop(columns=['Order_Cancelled'])\n",
    "y = dataCleaned['Order_Cancelled']\n",
    "X.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "sTsCfKePrnkU"
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report, roc_auc_score, roc_curve, precision_recall_curve, f1_score, make_scorer\n",
    "# Importing RocCurveDisplay and PrecisionRecallDisplay instead\n",
    "from sklearn.metrics import RocCurveDisplay, PrecisionRecallDisplay\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Split data into training and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Initialize and fit logistic regression model\n",
    "logreg_1 = LogisticRegression(max_iter=10000)\n",
    "logreg_1.fit(X_train, y_train)\n",
    "\n",
    "# Predict on training and test data\n",
    "y_train_pred = logreg_1.predict(X_train)\n",
    "y_test_pred = logreg_1.predict(X_test)\n",
    "\n",
    "# Get predicted probabilities for ROC-AUC, Precision-Recall, and Lift calculations\n",
    "y_train_prob = logreg_1.predict_proba(X_train)\n",
    "y_test_prob = logreg_1.predict_proba(X_test)\n",
    "\n",
    "# Get classification reports for training and test sets\n",
    "train_report = classification_report(y_train, y_train_pred, output_dict=True)\n",
    "test_report = classification_report(y_test, y_test_pred, output_dict=True)\n",
    "\n",
    "# Compute ROC-AUC scores for training and test sets\n",
    "train_roc_auc = roc_auc_score(y_train, logreg_1.predict_proba(X_train)[:, 1])\n",
    "test_roc_auc = roc_auc_score(y_test, logreg_1.predict_proba(X_test)[:, 1])\n",
    "\n",
    "# Compute confusion matrices for training and test sets\n",
    "train_conf_matrix = confusion_matrix(y_train, y_train_pred)\n",
    "test_conf_matrix = confusion_matrix(y_test, y_test_pred)\n",
    "\n",
    "# For later comprison\n",
    "X_train_prev = X_train\n",
    "y_train_prev = y_train\n",
    "X_test_prev = X_test\n",
    "y_test_prev = y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "_wuyfKPHxNO2",
    "outputId": "772a81d2-512f-413e-e5ff-d7be9eececea"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "y_train_norm shape: (3200,)\n",
      "y_train_pred shape: (3200,)\n",
      "y_test_norm shape: (800,)\n",
      "y_test_pred shape: (800,)\n"
     ]
    }
   ],
   "source": [
    "print(f\"y_train_norm shape: {y_train.shape}\")\n",
    "print(f\"y_train_pred shape: {y_train_pred.shape}\")\n",
    "print(f\"y_test_norm shape: {y_test.shape}\")\n",
    "print(f\"y_test_pred shape: {y_test_pred.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "TF5JzPDuwVid",
    "outputId": "6327b08a-e370-4cb7-ed88-f4e7d3cd37de"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification Report - Training Set:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.56      0.53      0.55      1592\n",
      "           1       0.56      0.59      0.57      1608\n",
      "\n",
      "    accuracy                           0.56      3200\n",
      "   macro avg       0.56      0.56      0.56      3200\n",
      "weighted avg       0.56      0.56      0.56      3200\n",
      "\n",
      "\n",
      "Classification Report - Test Set:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.56      0.55      0.55       398\n",
      "           1       0.56      0.57      0.57       402\n",
      "\n",
      "    accuracy                           0.56       800\n",
      "   macro avg       0.56      0.56      0.56       800\n",
      "weighted avg       0.56      0.56      0.56       800\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Print classification report\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "# Print the classification reports for the training and test sets\n",
    "print(\"Classification Report - Training Set:\")\n",
    "print(classification_report(y_train, y_train_pred))\n",
    "\n",
    "print(\"\\nClassification Report - Test Set:\")\n",
    "print(classification_report(y_test, y_test_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 407
    },
    "id": "f78o0i_-s8NC",
    "outputId": "4cf6dbd7-e047-4e07-f50b-840a1e32643d"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 600x400 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot confusion matrix for training set\n",
    "plt.figure(figsize=(6, 4))\n",
    "plt.subplot(1, 2, 1)\n",
    "sns.heatmap(train_conf_matrix, annot=True, fmt='d', cmap='Blues')\n",
    "plt.title('Confusion Matrix - Training Set')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "\n",
    "# Plot confusion matrix for test set\n",
    "plt.subplot(1, 2, 2)\n",
    "sns.heatmap(test_conf_matrix, annot=True, fmt='d', cmap='Blues')\n",
    "plt.title('Confusion Matrix - Test Set')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "# [TN FP​]\n",
    "# [FN TP]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 625
    },
    "id": "cD9PO_W8UIQo",
    "outputId": "e338d504-bca9-4a4e-a4de-7f8ec0b20ddc"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1600x700 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import RocCurveDisplay, PrecisionRecallDisplay\n",
    "from sklearn.metrics import precision_recall_curve\n",
    "\n",
    "# Helper function to compute cumulative gain and lift\n",
    "# Helper function to compute cumulative gain and lift\n",
    "def compute_lift(y_true, y_prob):\n",
    "    # Sort the predictions by the probabilities in descending order\n",
    "    sorted_indices = np.argsort(-y_prob)\n",
    "\n",
    "    # Get the values of y_true as a NumPy array to allow positional indexing\n",
    "    y_true_values = y_true.values\n",
    "    y_true_sorted = y_true_values[sorted_indices]\n",
    "\n",
    "    # Cumulative sum of positive instances\n",
    "    cumulative_positive = np.cumsum(y_true_sorted)\n",
    "    total_positives = np.sum(y_true_values) # Use y_true_values here too\n",
    "\n",
    "    # Cumulative gain is the ratio of cumulative positives to total positives\n",
    "    cumulative_gain = cumulative_positive / total_positives\n",
    "\n",
    "    # Lift is the cumulative gain divided by the baseline (which is the cumulative percentage of data)\n",
    "    percentage_data = np.arange(1, len(y_true_sorted) + 1) / len(y_true_sorted)\n",
    "    lift = cumulative_gain / percentage_data\n",
    "\n",
    "    return percentage_data, lift\n",
    "\n",
    "# Compute lift for the current and previous models\n",
    "percentage_data_1, lift_1 = compute_lift(y_test, logreg_1.predict_proba(X_test)[:, 1])\n",
    "\n",
    "plt.figure(figsize=(16, 7))\n",
    "\n",
    "# ROC curve with green for the current model and red for the previous model\n",
    "plt.subplot(1, 3, 1)\n",
    "ax1 = plt.gca()\n",
    "RocCurveDisplay.from_estimator(logreg_1, X_test, y_test, ax=ax1, color='red', name='Log-Reg-Base-Model')\n",
    "\n",
    "# Adding diagonal line for a random classifier\n",
    "ax1.plot([0, 1], [0, 1], 'k--', lw=2, label='Random Classifier')\n",
    "\n",
    "ax1.set_title('ROC Curve (Test Set)', fontsize=14)\n",
    "ax1.grid(True, which='both', linestyle='--', linewidth=0.5)\n",
    "ax1.minorticks_on()\n",
    "ax1.legend(loc='lower right')\n",
    "\n",
    "# Precision-Recall curve with green for the current model and red for the previous model\n",
    "plt.subplot(1, 3, 2)\n",
    "ax2 = plt.gca()\n",
    "PrecisionRecallDisplay.from_estimator(logreg_1, X_test, y_test, ax=ax2, color='red', name='Log-Reg-Base-Model')\n",
    "\n",
    "ax2.set_title('Precision-Recall Curve (Test Set)', fontsize=14)\n",
    "ax2.grid(True, which='both', linestyle='--', linewidth=0.5)\n",
    "ax2.minorticks_on()\n",
    "\n",
    "# Lift curve\n",
    "plt.subplot(1, 3, 3)\n",
    "plt.plot(percentage_data_1, lift_1, label='Log-Reg-Base-Model', color='red')\n",
    "\n",
    "plt.title('Lift Curve (Test Set)', fontsize=14)\n",
    "plt.xlabel('Percentage of Data', fontsize=12)\n",
    "plt.ylabel('Lift', fontsize=12)\n",
    "\n",
    "# Enable both major and minor ticks\n",
    "plt.minorticks_on()\n",
    "\n",
    "# Major and minor gridlines\n",
    "plt.grid(True, which='major', linestyle='-', linewidth=0.7)  # Major gridlines\n",
    "plt.grid(True, which='minor', linestyle='--', linewidth=0.3)  # Minor gridlines\n",
    "\n",
    "plt.legend(loc='best')\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "fZY5QmAUymbY"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.metrics import precision_score, recall_score, f1_score, roc_auc_score, accuracy_score, cohen_kappa_score, classification_report\n",
    "import numpy as np\n",
    "\n",
    "# Initialize the DataFrame to store the classification metrics\n",
    "scores = pd.DataFrame(columns=[\n",
    "    'Model',\n",
    "    'Accuracy_Train', 'Precision_Train', 'Recall_Train', 'F1_Train', 'ROC_AUC_Train', 'Cohen_Kappa_Train',\n",
    "    'Accuracy_Test', 'Precision_Test', 'Recall_Test', 'F1_Test', 'ROC_AUC_Test', 'Cohen_Kappa_Test'\n",
    "])\n",
    "\n",
    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score, cohen_kappa_score\n",
    "import pandas as pd\n",
    "\n",
    "def get_classification_metrics(y_train, y_train_pred, y_train_prob, y_test, y_test_pred, y_test_prob, model_name, scores):\n",
    "    # Train metrics\n",
    "    accuracy_train = accuracy_score(y_train, y_train_pred)\n",
    "    precision_train = precision_score(y_train, y_train_pred, zero_division=0)\n",
    "    recall_train = recall_score(y_train, y_train_pred, zero_division=0)\n",
    "    f1_train = f1_score(y_train, y_train_pred, zero_division=0)\n",
    "    roc_auc_train = roc_auc_score(y_train, y_train_prob[:, 1]) if len(set(y_train)) == 2 else float('nan')\n",
    "    cohen_kappa_train = cohen_kappa_score(y_train, y_train_pred)\n",
    "\n",
    "    # Weighted and macro averages for training\n",
    "    weighted_precision_train = precision_score(y_train, y_train_pred, average='weighted', zero_division=0)\n",
    "    weighted_recall_train = recall_score(y_train, y_train_pred, average='weighted', zero_division=0)\n",
    "    macro_precision_train = precision_score(y_train, y_train_pred, average='macro', zero_division=0)\n",
    "    macro_recall_train = recall_score(y_train, y_train_pred, average='macro', zero_division=0)\n",
    "\n",
    "    # Test metrics\n",
    "    accuracy_test = accuracy_score(y_test, y_test_pred)\n",
    "    precision_test = precision_score(y_test, y_test_pred, zero_division=0)\n",
    "    recall_test = recall_score(y_test, y_test_pred, zero_division=0)\n",
    "    f1_test = f1_score(y_test, y_test_pred, zero_division=0)\n",
    "    roc_auc_test = roc_auc_score(y_test, y_test_prob[:, 1]) if len(set(y_test)) == 2 else float('nan')\n",
    "    cohen_kappa_test = cohen_kappa_score(y_test, y_test_pred)\n",
    "\n",
    "    # Weighted and macro averages for test\n",
    "    weighted_precision_test = precision_score(y_test, y_test_pred, average='weighted', zero_division=0)\n",
    "    weighted_recall_test = recall_score(y_test, y_test_pred, average='weighted', zero_division=0)\n",
    "    macro_precision_test = precision_score(y_test, y_test_pred, average='macro', zero_division=0)\n",
    "    macro_recall_test = recall_score(y_test, y_test_pred, average='macro', zero_division=0)\n",
    "\n",
    "    # Create a DataFrame with new metrics\n",
    "    new_metrics = pd.DataFrame({\n",
    "        'Model': [model_name],\n",
    "        'Accuracy_Train': [accuracy_train],\n",
    "        'Precision_Train': [precision_train],\n",
    "        'Recall_Train': [recall_train],\n",
    "        'F1_Train': [f1_train],\n",
    "        'ROC_AUC_Train': [roc_auc_train],\n",
    "        'Cohen_Kappa_Train': [cohen_kappa_train],\n",
    "        'Weighted_Precision_Train': [weighted_precision_train],\n",
    "        'Weighted_Recall_Train': [weighted_recall_train],\n",
    "        'Macro_Precision_Train': [macro_precision_train],\n",
    "        'Macro_Recall_Train': [macro_recall_train],\n",
    "        'Accuracy_Test': [accuracy_test],\n",
    "        'Precision_Test': [precision_test],\n",
    "        'Recall_Test': [recall_test],\n",
    "        'F1_Test': [f1_test],\n",
    "        'ROC_AUC_Test': [roc_auc_test],\n",
    "        'Cohen_Kappa_Test': [cohen_kappa_test],\n",
    "        'Weighted_Precision_Test': [weighted_precision_test],\n",
    "        'Weighted_Recall_Test': [weighted_recall_test],\n",
    "        'Macro_Precision_Test': [macro_precision_test],\n",
    "        'Macro_Recall_Test': [macro_recall_test]\n",
    "    })\n",
    "\n",
    "\n",
    "    # Append the new metrics to the existing scores DataFrame\n",
    "    scores = pd.concat([scores, new_metrics], ignore_index=True)\n",
    "\n",
    "    return scores\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 184
    },
    "id": "AhelBuhK4neK",
    "outputId": "0260a088-6a37-44f8-825d-25b458855c45"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-15-2b0b5e3a7f8f>:71: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
      "  scores = pd.concat([scores, new_metrics], ignore_index=True)\n"
     ]
    },
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "scores"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-63a332e6-3795-4a59-be0a-7a1188f44b3a\" 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>Model</th>\n",
       "      <th>Accuracy_Train</th>\n",
       "      <th>Precision_Train</th>\n",
       "      <th>Recall_Train</th>\n",
       "      <th>F1_Train</th>\n",
       "      <th>ROC_AUC_Train</th>\n",
       "      <th>Cohen_Kappa_Train</th>\n",
       "      <th>Accuracy_Test</th>\n",
       "      <th>Precision_Test</th>\n",
       "      <th>Recall_Test</th>\n",
       "      <th>...</th>\n",
       "      <th>ROC_AUC_Test</th>\n",
       "      <th>Cohen_Kappa_Test</th>\n",
       "      <th>Weighted_Precision_Train</th>\n",
       "      <th>Weighted_Recall_Train</th>\n",
       "      <th>Macro_Precision_Train</th>\n",
       "      <th>Macro_Recall_Train</th>\n",
       "      <th>Weighted_Precision_Test</th>\n",
       "      <th>Weighted_Recall_Test</th>\n",
       "      <th>Macro_Precision_Test</th>\n",
       "      <th>Macro_Recall_Test</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Logistic Regression</td>\n",
       "      <td>0.560625</td>\n",
       "      <td>0.559905</td>\n",
       "      <td>0.587065</td>\n",
       "      <td>0.573163</td>\n",
       "      <td>0.587135</td>\n",
       "      <td>0.121014</td>\n",
       "      <td>0.56</td>\n",
       "      <td>0.56068</td>\n",
       "      <td>0.574627</td>\n",
       "      <td>...</td>\n",
       "      <td>0.576146</td>\n",
       "      <td>0.119868</td>\n",
       "      <td>0.560662</td>\n",
       "      <td>0.560625</td>\n",
       "      <td>0.560666</td>\n",
       "      <td>0.560492</td>\n",
       "      <td>0.559982</td>\n",
       "      <td>0.56</td>\n",
       "      <td>0.559979</td>\n",
       "      <td>0.559926</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 21 columns</p>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-63a332e6-3795-4a59-be0a-7a1188f44b3a')\"\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-63a332e6-3795-4a59-be0a-7a1188f44b3a 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-63a332e6-3795-4a59-be0a-7a1188f44b3a');\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=\"id_10ea077d-de96-4e4e-a825-a2edf8d44ee4\">\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('scores')\"\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_10ea077d-de96-4e4e-a825-a2edf8d44ee4 button.colab-df-generate');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      buttonEl.onclick = () => {\n",
       "        google.colab.notebook.generateWithVariable('scores');\n",
       "      }\n",
       "      })();\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "                 Model  Accuracy_Train  Precision_Train  Recall_Train  \\\n",
       "0  Logistic Regression        0.560625         0.559905      0.587065   \n",
       "\n",
       "   F1_Train  ROC_AUC_Train  Cohen_Kappa_Train  Accuracy_Test  Precision_Test  \\\n",
       "0  0.573163       0.587135           0.121014           0.56         0.56068   \n",
       "\n",
       "   Recall_Test  ...  ROC_AUC_Test  Cohen_Kappa_Test  Weighted_Precision_Train  \\\n",
       "0     0.574627  ...      0.576146          0.119868                  0.560662   \n",
       "\n",
       "   Weighted_Recall_Train  Macro_Precision_Train  Macro_Recall_Train  \\\n",
       "0               0.560625               0.560666            0.560492   \n",
       "\n",
       "   Weighted_Precision_Test  Weighted_Recall_Test  Macro_Precision_Test  \\\n",
       "0                 0.559982                  0.56              0.559979   \n",
       "\n",
       "   Macro_Recall_Test  \n",
       "0           0.559926  \n",
       "\n",
       "[1 rows x 21 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Assuming you have a trained classification model (e.g., logistic regression or any other binary classifier)\n",
    "# Train the model\n",
    "\n",
    "# Call the classification metrics function\n",
    "scores = get_classification_metrics(\n",
    "    y_train=y_train,\n",
    "    y_train_pred=y_train_pred,\n",
    "    y_train_prob=y_train_prob,\n",
    "    y_test=y_test,\n",
    "    y_test_pred=y_test_pred,\n",
    "    y_test_prob=y_test_prob,\n",
    "    model_name=\"Logistic Regression\",\n",
    "    scores=scores\n",
    ")\n",
    "\n",
    "# Display the updated scores DataFrame\n",
    "scores\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "FtGisqysq01J"
   },
   "source": [
    "### Add model explainability:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 870
    },
    "id": "Bu-NJSBjq0Gw",
    "outputId": "778467cb-e4cf-415b-a0bc-71b08ef86f27"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.10/dist-packages/shap/explainers/_linear.py:95: FutureWarning: The feature_perturbation option is now deprecated in favor of using the appropriate masker (maskers.Independent, maskers.Partition or maskers.Impute).\n",
      "  warnings.warn(wmsg, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x790 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import shap\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pandas as pd\n",
    "import numpy as np  # Import numpy\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "# ... your existing code ...\n",
    "model = logreg_1\n",
    "# Convert shap_values to numeric if necessary:\n",
    "# Iterate over columns and convert to numeric, if applicable\n",
    "for col in X_train.columns:\n",
    "    try:\n",
    "        X_train[col] = pd.to_numeric(X_train[col])\n",
    "    except ValueError:\n",
    "        print(f\"Column {col} could not be converted to numeric, skipping...\")\n",
    "\n",
    "# Sample background data to speed up SHAP calculations\n",
    "# Use SHAP LinearExplainer, which is faster for linear models like Logistic Regression\n",
    "explainer = shap.LinearExplainer(model, X_train, feature_perturbation=\"interventional\")\n",
    "shap_values = explainer.shap_values(X_train)\n",
    "\n",
    "# Convert shap_values data to numpy array with dtype=float64 before plotting\n",
    "shap_values_numeric = shap_values.astype(np.float64)\n",
    "\n",
    "# Plot the SHAP summary plot for model explainability\n",
    "shap.summary_plot(shap_values_numeric, X_train, show=False)\n",
    "plt.title('SHAP Summary Plot - Logistic Regression Model Explainability')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "nrfmNBwXDkWb",
    "outputId": "d5e47604-f719-4e25-8c6f-8027da59a42e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Days_to_Delivery', 'Num_Items_Ordered', 'Order_Value', 'Discount_Rate',\n",
       "       'Num_Previous_Orders', 'Delivery_Time_Variation', 'Product_Category',\n",
       "       'Order_Cancelled', 'Correlated_Order_Value', 'Region_EMEA',\n",
       "       'Region_LATAM', 'Region_North America', 'Order_Priority_Low',\n",
       "       'Order_Priority_Medium', 'Payment_Method_Bitcoin',\n",
       "       'Payment_Method_Credit Card', 'Payment_Method_PayPal'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataCleaned.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "p_N2w5P0DWXM"
   },
   "source": [
    "### Check Multicolinearity: Compute the Variance Inflation Factor (VIF):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 212
    },
    "id": "0zoPSTqJEN_l",
    "outputId": "6994e0d6-6824-415b-9a46-9a3a0a6660d4"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"dataCleanedCopyFirst\",\n  \"rows\": 4000,\n  \"fields\": [\n    {\n      \"column\": \"Days_to_Delivery\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.994307840004563,\n        \"min\": -1.4825346801381452,\n        \"max\": 12.852475412872652,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          4.588281138239319,\n          6.848540279075659,\n          4.583766285454921\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Items_Ordered\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5.5100269542679365,\n        \"min\": 1.0,\n        \"max\": 19.0,\n        \"num_unique_values\": 19,\n        \"samples\": [\n          16.0,\n          7.0,\n          12.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 100.2130314677825,\n        \"min\": 130.3378094310662,\n        \"max\": 841.4187025980059,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          534.0622328238003,\n          732.0218220267479,\n          485.5762040062945\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Discount_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.14292836009448692,\n        \"min\": 8.775792896165147e-05,\n        \"max\": 0.4999463333525246,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.131760721241866,\n          0.3155826053495354,\n          0.31135019811647\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Previous_Orders\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.836039089457201,\n        \"min\": 0.0,\n        \"max\": 9.0,\n        \"num_unique_values\": 10,\n        \"samples\": [\n          0.0,\n          2.0,\n          3.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Delivery_Time_Variation\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8716236709628011,\n        \"min\": 0.0006041944029312,\n        \"max\": 2.99946649608437,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          0.7979158312926778,\n          2.8416834043829686,\n          2.144395823199287\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Product_Category\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.07073999886887665,\n        \"min\": 0.29508196721311475,\n        \"max\": 0.6615384615384615,\n        \"num_unique_values\": 56,\n        \"samples\": [\n          0.4470588235294118,\n          0.45901639344262296,\n          0.5079365079365079\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Cancelled\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1,\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Correlated_Order_Value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 95.35982445380614,\n        \"min\": 120.4281477270148,\n        \"max\": 791.0946013871961,\n        \"num_unique_values\": 4000,\n        \"samples\": [\n          504.113753506419,\n          699.9149033564593\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_EMEA\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_LATAM\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_North America\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Low\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Medium\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Bitcoin\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Credit Card\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_PayPal\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "dataCleanedCopyFirst"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-7a3614b9-4c92-4154-a978-e6dab69379f0\" 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>Days_to_Delivery</th>\n",
       "      <th>Num_Items_Ordered</th>\n",
       "      <th>Order_Value</th>\n",
       "      <th>Discount_Rate</th>\n",
       "      <th>Num_Previous_Orders</th>\n",
       "      <th>Delivery_Time_Variation</th>\n",
       "      <th>Product_Category</th>\n",
       "      <th>Order_Cancelled</th>\n",
       "      <th>Correlated_Order_Value</th>\n",
       "      <th>Region_EMEA</th>\n",
       "      <th>Region_LATAM</th>\n",
       "      <th>Region_North America</th>\n",
       "      <th>Order_Priority_Low</th>\n",
       "      <th>Order_Priority_Medium</th>\n",
       "      <th>Payment_Method_Bitcoin</th>\n",
       "      <th>Payment_Method_Credit Card</th>\n",
       "      <th>Payment_Method_PayPal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.176246</td>\n",
       "      <td>16.0</td>\n",
       "      <td>532.685241</td>\n",
       "      <td>0.100711</td>\n",
       "      <td>8.0</td>\n",
       "      <td>1.601869</td>\n",
       "      <td>0.447059</td>\n",
       "      <td>0</td>\n",
       "      <td>505.651649</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.573086</td>\n",
       "      <td>8.0</td>\n",
       "      <td>367.854514</td>\n",
       "      <td>0.117976</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.425666</td>\n",
       "      <td>0.592105</td>\n",
       "      <td>0</td>\n",
       "      <td>348.849923</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.096170</td>\n",
       "      <td>13.0</td>\n",
       "      <td>640.514439</td>\n",
       "      <td>0.292261</td>\n",
       "      <td>9.0</td>\n",
       "      <td>2.622599</td>\n",
       "      <td>0.563636</td>\n",
       "      <td>0</td>\n",
       "      <td>611.311508</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.327226</td>\n",
       "      <td>10.0</td>\n",
       "      <td>434.579153</td>\n",
       "      <td>0.243082</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0.472247</td>\n",
       "      <td>0.545455</td>\n",
       "      <td>1</td>\n",
       "      <td>412.479846</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</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-7a3614b9-4c92-4154-a978-e6dab69379f0')\"\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-7a3614b9-4c92-4154-a978-e6dab69379f0 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-7a3614b9-4c92-4154-a978-e6dab69379f0');\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-a04d010e-f6a3-4782-82aa-3548301246bc\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-a04d010e-f6a3-4782-82aa-3548301246bc')\"\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-a04d010e-f6a3-4782-82aa-3548301246bc button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   Days_to_Delivery  Num_Items_Ordered  Order_Value  Discount_Rate  \\\n",
       "0          4.176246               16.0   532.685241       0.100711   \n",
       "1          4.573086                8.0   367.854514       0.117976   \n",
       "2          5.096170               13.0   640.514439       0.292261   \n",
       "3          4.327226               10.0   434.579153       0.243082   \n",
       "\n",
       "   Num_Previous_Orders  Delivery_Time_Variation  Product_Category  \\\n",
       "0                  8.0                 1.601869          0.447059   \n",
       "1                  2.0                 2.425666          0.592105   \n",
       "2                  9.0                 2.622599          0.563636   \n",
       "3                  8.0                 0.472247          0.545455   \n",
       "\n",
       "   Order_Cancelled  Correlated_Order_Value  Region_EMEA  Region_LATAM  \\\n",
       "0                0              505.651649        False         False   \n",
       "1                0              348.849923        False         False   \n",
       "2                0              611.311508        False         False   \n",
       "3                1              412.479846        False          True   \n",
       "\n",
       "   Region_North America  Order_Priority_Low  Order_Priority_Medium  \\\n",
       "0                 False                True                  False   \n",
       "1                  True               False                   True   \n",
       "2                 False               False                   True   \n",
       "3                 False                True                  False   \n",
       "\n",
       "   Payment_Method_Bitcoin  Payment_Method_Credit Card  Payment_Method_PayPal  \n",
       "0                   False                        True                  False  \n",
       "1                   False                       False                   True  \n",
       "2                   False                       False                   True  \n",
       "3                   False                       False                   True  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataCleanedCopyFirst = dataCleaned.copy()\n",
    "dataCleanedCopyFirst.head(4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 175
    },
    "id": "oeimkqESDUpv",
    "outputId": "9e481379-5e1f-4d57-bbfe-e6f2922f461b"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"top_4_vif_features\",\n  \"rows\": 4,\n  \"fields\": [\n    {\n      \"column\": \"feature\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"Correlated_Order_Value\",\n          \"Days_to_Delivery\",\n          \"Order_Value\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"VIF\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5371.41286690576,\n        \"min\": 6.810394966565397,\n        \"max\": 9328.682623992208,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          9309.03548585529,\n          6.810394966565397,\n          9328.682623992208\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "top_4_vif_features"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-34696e4c-0678-4c99-bf07-83a49d9c3175\" 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>feature</th>\n",
       "      <th>VIF</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Order_Value</td>\n",
       "      <td>9328.682624</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Correlated_Order_Value</td>\n",
       "      <td>9309.035486</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Product_Category</td>\n",
       "      <td>23.824029</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Days_to_Delivery</td>\n",
       "      <td>6.810395</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-34696e4c-0678-4c99-bf07-83a49d9c3175')\"\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-34696e4c-0678-4c99-bf07-83a49d9c3175 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-34696e4c-0678-4c99-bf07-83a49d9c3175');\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-b795dab6-ddf2-435f-8a35-20fc052e8d2c\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-b795dab6-ddf2-435f-8a35-20fc052e8d2c')\"\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-b795dab6-ddf2-435f-8a35-20fc052e8d2c button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "  <div id=\"id_7cb31913-5098-4822-97ba-f28300213ac2\">\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('top_4_vif_features')\"\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_7cb31913-5098-4822-97ba-f28300213ac2 button.colab-df-generate');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      buttonEl.onclick = () => {\n",
       "        google.colab.notebook.generateWithVariable('top_4_vif_features');\n",
       "      }\n",
       "      })();\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "                  feature          VIF\n",
       "2             Order_Value  9328.682624\n",
       "7  Correlated_Order_Value  9309.035486\n",
       "6        Product_Category    23.824029\n",
       "0        Days_to_Delivery     6.810395"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Import the necessary function\n",
    "from statsmodels.stats.outliers_influence import variance_inflation_factor\n",
    "\n",
    "# Calculate VIF for all features\n",
    "X = dataCleanedCopyFirst.drop(columns=['Order_Cancelled'])\n",
    "\n",
    "# Select only numeric columns for VIF calculation\n",
    "X = X.select_dtypes(include=np.number)  # Filter for numeric columns only\n",
    "\n",
    "vif_data = pd.DataFrame()\n",
    "vif_data[\"feature\"] = X.columns\n",
    "vif_data[\"VIF\"] = [variance_inflation_factor(X.values, i) for i in range(X.shape[1])]\n",
    "\n",
    "# Sort VIF values in descending order\n",
    "vif_data_sorted = vif_data.sort_values(by=\"VIF\", ascending=False)\n",
    "\n",
    "# Display the top 4 features with the highest VIF\n",
    "top_4_vif_features = vif_data_sorted.head(4)\n",
    "top_4_vif_features\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "kULNgbKTG1Xu"
   },
   "source": [
    "### Remove features with high VIF values:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "BFxQC1Cxymeo"
   },
   "outputs": [],
   "source": [
    "# Remove the two features with the highest VIF (Order_Value and Correlated_Order_Value)\n",
    "dataCleanedCopyFirst_reduced = dataCleanedCopyFirst.drop(columns=['Order_Value', 'Correlated_Order_Value'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qdgrSQ9CGSnm"
   },
   "source": [
    "### Influential data points analysis:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "j6ADSjf3ymhE",
    "outputId": "f6a579f1-fb26-4903-8da1-1fa1cd8fd032"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(pandas.core.frame.DataFrame, pandas.core.series.Series)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "\n",
    "# Adding a constant for logistic regression with statsmodels\n",
    "# Logit() from statsmodels can only accept numeric features\n",
    "X = dataCleanedCopyFirst_reduced.drop(['Order_Cancelled', 'Region_EMEA',\t'Region_LATAM',\t'Region_North America',\t'Order_Priority_Low',\t'Order_Priority_Medium',\t'Payment_Method_Bitcoin',\t'Payment_Method_Credit Card',\t'Payment_Method_PayPal'], axis=1)\n",
    "X_reduced = sm.add_constant(X)\n",
    "\n",
    "# Target variable\n",
    "y_reduced = dataCleanedCopyFirst_reduced['Order_Cancelled']\n",
    "type(X_reduced), type(y_reduced)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 249
    },
    "id": "6mvkous3NtFF",
    "outputId": "336ee1d0-b582-457e-cb45-0dab6267572c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Optimization terminated successfully.\n",
      "         Current function value: 0.681856\n",
      "         Iterations 4\n"
     ]
    },
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"high_influence_points\",\n  \"rows\": 17,\n  \"fields\": [\n    {\n      \"column\": \"dfb_const\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.02277806177504171,\n        \"min\": 0.008625315390756354,\n        \"max\": 0.0808024497590017,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          0.04638402105662976,\n          0.01926373769115549,\n          0.04172368088007894\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dfb_Days_to_Delivery\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.034066602066676534,\n        \"min\": -0.04285855187383463,\n        \"max\": 0.06409982274924397,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          -0.04285855187383463,\n          0.043469515848355046,\n          0.005027666872327656\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dfb_Num_Items_Ordered\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.025187525783886274,\n        \"min\": -0.03348249954026637,\n        \"max\": 0.03318185503049964,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          0.024424363065082014,\n          0.03318185503049964,\n          0.019382339765945663\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dfb_Discount_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.027666358236359424,\n        \"min\": -0.035330737103256384,\n        \"max\": 0.04216789091739003,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          -0.035330737103256384,\n          0.03590252954081408,\n          0.035790299318248286\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dfb_Num_Previous_Orders\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.027464981539814307,\n        \"min\": -0.034014621341817375,\n        \"max\": 0.038426887975496024,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          0.03077450631281765,\n          0.030103445122257003,\n          0.029380108332736108\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dfb_Delivery_Time_Variation\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.025118521300368908,\n        \"min\": -0.03397249544647702,\n        \"max\": 0.036135569916364886,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          -0.026125239045269304,\n          0.036135569916364886,\n          0.00546168653699509\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dfb_Product_Category\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.010776558364414792,\n        \"min\": -0.07376142589807375,\n        \"max\": -0.040853869082930525,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          -0.040853869082930525,\n          -0.06682558326604893,\n          -0.0689892192532471\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"cooks_d\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0001865985760428531,\n        \"min\": 0.0010032061793420486,\n        \"max\": 0.0016472770236543885,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          0.0010719981639282258,\n          0.0016472770236543885,\n          0.0011192218751295998\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"standard_resid\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.1541025430442953,\n        \"min\": -1.500194963832094,\n        \"max\": 1.699006149995791,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          -1.3295717491968682,\n          1.5714971185161248,\n          1.5924467889612646\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"hat_diag\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0005445100590621817,\n        \"min\": 0.002938984620279304,\n        \"max\": 0.004817125785695291,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          0.004226967268855192,\n          0.00464744691298543,\n          0.0030799573196982435\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dffits_internal\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.07115414947201538,\n        \"min\": -0.10017881651831458,\n        \"max\": 0.10738221065698321,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          -0.08662555712662164,\n          0.10738221065698321,\n          0.08851301105434838\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "high_influence_points"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-8e5f8840-c6e4-40b5-9075-5a9ebeb7e4ee\" 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>dfb_const</th>\n",
       "      <th>dfb_Days_to_Delivery</th>\n",
       "      <th>dfb_Num_Items_Ordered</th>\n",
       "      <th>dfb_Discount_Rate</th>\n",
       "      <th>dfb_Num_Previous_Orders</th>\n",
       "      <th>dfb_Delivery_Time_Variation</th>\n",
       "      <th>dfb_Product_Category</th>\n",
       "      <th>cooks_d</th>\n",
       "      <th>standard_resid</th>\n",
       "      <th>hat_diag</th>\n",
       "      <th>dffits_internal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>262</th>\n",
       "      <td>0.046384</td>\n",
       "      <td>-0.042859</td>\n",
       "      <td>0.024424</td>\n",
       "      <td>-0.035331</td>\n",
       "      <td>0.030775</td>\n",
       "      <td>-0.026125</td>\n",
       "      <td>-0.040854</td>\n",
       "      <td>0.001072</td>\n",
       "      <td>-1.329572</td>\n",
       "      <td>0.004227</td>\n",
       "      <td>-0.086626</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>393</th>\n",
       "      <td>0.019264</td>\n",
       "      <td>0.043470</td>\n",
       "      <td>0.033182</td>\n",
       "      <td>0.035903</td>\n",
       "      <td>0.030103</td>\n",
       "      <td>0.036136</td>\n",
       "      <td>-0.066826</td>\n",
       "      <td>0.001647</td>\n",
       "      <td>1.571497</td>\n",
       "      <td>0.004647</td>\n",
       "      <td>0.107382</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>534</th>\n",
       "      <td>0.059447</td>\n",
       "      <td>-0.039639</td>\n",
       "      <td>0.018373</td>\n",
       "      <td>0.001860</td>\n",
       "      <td>0.019389</td>\n",
       "      <td>0.015256</td>\n",
       "      <td>-0.066324</td>\n",
       "      <td>0.001071</td>\n",
       "      <td>1.500654</td>\n",
       "      <td>0.003317</td>\n",
       "      <td>0.086574</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>551</th>\n",
       "      <td>0.033917</td>\n",
       "      <td>0.064100</td>\n",
       "      <td>-0.026861</td>\n",
       "      <td>0.002745</td>\n",
       "      <td>-0.016950</td>\n",
       "      <td>-0.007884</td>\n",
       "      <td>-0.047827</td>\n",
       "      <td>0.001155</td>\n",
       "      <td>1.419833</td>\n",
       "      <td>0.003994</td>\n",
       "      <td>0.089913</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-8e5f8840-c6e4-40b5-9075-5a9ebeb7e4ee')\"\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-8e5f8840-c6e4-40b5-9075-5a9ebeb7e4ee 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-8e5f8840-c6e4-40b5-9075-5a9ebeb7e4ee');\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-469c09bc-2134-47d1-a09e-b1a83e0a67c8\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-469c09bc-2134-47d1-a09e-b1a83e0a67c8')\"\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-469c09bc-2134-47d1-a09e-b1a83e0a67c8 button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "     dfb_const  dfb_Days_to_Delivery  dfb_Num_Items_Ordered  \\\n",
       "262   0.046384             -0.042859               0.024424   \n",
       "393   0.019264              0.043470               0.033182   \n",
       "534   0.059447             -0.039639               0.018373   \n",
       "551   0.033917              0.064100              -0.026861   \n",
       "\n",
       "     dfb_Discount_Rate  dfb_Num_Previous_Orders  dfb_Delivery_Time_Variation  \\\n",
       "262          -0.035331                 0.030775                    -0.026125   \n",
       "393           0.035903                 0.030103                     0.036136   \n",
       "534           0.001860                 0.019389                     0.015256   \n",
       "551           0.002745                -0.016950                    -0.007884   \n",
       "\n",
       "     dfb_Product_Category   cooks_d  standard_resid  hat_diag  dffits_internal  \n",
       "262             -0.040854  0.001072       -1.329572  0.004227        -0.086626  \n",
       "393             -0.066826  0.001647        1.571497  0.004647         0.107382  \n",
       "534             -0.066324  0.001071        1.500654  0.003317         0.086574  \n",
       "551             -0.047827  0.001155        1.419833  0.003994         0.089913  "
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "# Fit a logistic regression model using statsmodels to check for influential points\n",
    "logit_model = sm.Logit(y_reduced, X_reduced)\n",
    "result = logit_model.fit()\n",
    "\n",
    "# Influence summary (e.g., Cook's distance)\n",
    "influence = result.get_influence()\n",
    "\n",
    "# Obtain the summary frame for influence measures\n",
    "summary_frame = influence.summary_frame()\n",
    "\n",
    "# Check for high influence points based on Cook's distance\n",
    "high_influence_points = summary_frame[summary_frame['cooks_d'] > 4 / len(X_reduced)]\n",
    "\n",
    "# Display high influence points\n",
    "high_influence_points.head(4)  # Show top 4 and the count of high influence points\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "_XT6_vnbymie",
    "outputId": "30bbabda-ff69-4445-ef44-28def5b3bac1"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "17"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "high_influence_points.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MQQc3SrMRLg1"
   },
   "source": [
    "### Drop the high influence data points from the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "FwQiciaUQwX4",
    "outputId": "99db112c-30ab-40cf-91dc-6a3f757d6485"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3983,)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Drop the high influence points based on Cook's distance\n",
    "from sklearn.preprocessing import RobustScaler\n",
    "\n",
    "# Dropping influential data points from X and y\n",
    "X_reduced_no_infl_all_attribs = dataCleanedCopyFirst_reduced.drop(index=high_influence_points.index)\n",
    "\n",
    "# Ensure y_reduced_no_infl_all_attribs only includes the target column 'Order_Cancelled'\n",
    "y_reduced_no_infl_all_attribs = dataCleanedCopyFirst_reduced.loc[~dataCleanedCopyFirst_reduced.index.isin(high_influence_points.index), 'Order_Cancelled']\n",
    "\n",
    "y_reduced_no_infl_all_attribs.shape\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "hztbCMqoP3A8"
   },
   "source": [
    "### Now apply normalization:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 243
    },
    "id": "GTCNHHyTcaMg",
    "outputId": "2249e308-dfe8-4d55-cb7d-f04a4207c34d"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"X_reduced_no_infl_all_attribs_scaled\",\n  \"rows\": 3983,\n  \"fields\": [\n    {\n      \"column\": \"Days_to_Delivery\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.7514573293242675,\n        \"min\": -2.4654922754237965,\n        \"max\": 2.9545010964178764,\n        \"num_unique_values\": 3983,\n        \"samples\": [\n          0.14309757782489255,\n          -0.6786582013918893,\n          0.9218975319978105\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Items_Ordered\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.550698932241222,\n        \"min\": -0.9,\n        \"max\": 0.9,\n        \"num_unique_values\": 19,\n        \"samples\": [\n          0.6,\n          -0.3,\n          0.2\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Discount_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5913415778761281,\n        \"min\": -1.0195237175983298,\n        \"max\": 1.0504365696898748,\n        \"num_unique_values\": 3983,\n        \"samples\": [\n          -0.3059911191729756,\n          0.04495535456257886,\n          0.0030089465153978643\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Num_Previous_Orders\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5664572037866893,\n        \"min\": -0.8,\n        \"max\": 1.0,\n        \"num_unique_values\": 10,\n        \"samples\": [\n          -0.8,\n          -0.4,\n          -0.2\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Delivery_Time_Variation\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5742227653573563,\n        \"min\": -0.9861633813765495,\n        \"max\": 0.9902776184000186,\n        \"num_unique_values\": 3983,\n        \"samples\": [\n          -0.5565145408613797,\n          -0.6780477496925864,\n          -0.4440459493175594\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Product_Category\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.7610095109825092,\n        \"min\": -2.234455958549223,\n        \"max\": 1.7614388202471103,\n        \"num_unique_values\": 56,\n        \"samples\": [\n          -0.5772782688204814,\n          -0.4468911917098445,\n          0.08654083395016007\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Cancelled\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1,\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_EMEA\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_LATAM\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Region_North America\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Low\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Order_Priority_Medium\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Bitcoin\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_Credit Card\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          false,\n          true\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Payment_Method_PayPal\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "X_reduced_no_infl_all_attribs_scaled"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-f8e13143-fd26-435e-9a90-bda518ad0df8\" 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>Days_to_Delivery</th>\n",
       "      <th>Num_Items_Ordered</th>\n",
       "      <th>Discount_Rate</th>\n",
       "      <th>Num_Previous_Orders</th>\n",
       "      <th>Delivery_Time_Variation</th>\n",
       "      <th>Product_Category</th>\n",
       "      <th>Order_Cancelled</th>\n",
       "      <th>Region_EMEA</th>\n",
       "      <th>Region_LATAM</th>\n",
       "      <th>Region_North America</th>\n",
       "      <th>Order_Priority_Low</th>\n",
       "      <th>Order_Priority_Medium</th>\n",
       "      <th>Payment_Method_Bitcoin</th>\n",
       "      <th>Payment_Method_Credit Card</th>\n",
       "      <th>Payment_Method_PayPal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.325936</td>\n",
       "      <td>0.6</td>\n",
       "      <td>-0.602800</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.069172</td>\n",
       "      <td>-0.577278</td>\n",
       "      <td>0</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.175893</td>\n",
       "      <td>-0.2</td>\n",
       "      <td>-0.531301</td>\n",
       "      <td>-0.4</td>\n",
       "      <td>0.612107</td>\n",
       "      <td>1.004329</td>\n",
       "      <td>0</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.021882</td>\n",
       "      <td>0.3</td>\n",
       "      <td>0.190483</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.741898</td>\n",
       "      <td>0.693900</td>\n",
       "      <td>0</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.268852</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.013184</td>\n",
       "      <td>0.8</td>\n",
       "      <td>-0.675321</td>\n",
       "      <td>0.495643</td>\n",
       "      <td>1</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.809206</td>\n",
       "      <td>-0.9</td>\n",
       "      <td>-0.509595</td>\n",
       "      <td>-0.4</td>\n",
       "      <td>-0.455535</td>\n",
       "      <td>-0.804404</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</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-f8e13143-fd26-435e-9a90-bda518ad0df8')\"\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-f8e13143-fd26-435e-9a90-bda518ad0df8 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-f8e13143-fd26-435e-9a90-bda518ad0df8');\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-878383c5-154b-497a-a92c-2247c58b3a59\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-878383c5-154b-497a-a92c-2247c58b3a59')\"\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-878383c5-154b-497a-a92c-2247c58b3a59 button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   Days_to_Delivery  Num_Items_Ordered  Discount_Rate  Num_Previous_Orders  \\\n",
       "0         -0.325936                0.6      -0.602800                  0.8   \n",
       "1         -0.175893               -0.2      -0.531301                 -0.4   \n",
       "2          0.021882                0.3       0.190483                  1.0   \n",
       "3         -0.268852                0.0      -0.013184                  0.8   \n",
       "4          1.809206               -0.9      -0.509595                 -0.4   \n",
       "\n",
       "   Delivery_Time_Variation  Product_Category  Order_Cancelled  Region_EMEA  \\\n",
       "0                 0.069172         -0.577278                0        False   \n",
       "1                 0.612107          1.004329                0        False   \n",
       "2                 0.741898          0.693900                0        False   \n",
       "3                -0.675321          0.495643                1        False   \n",
       "4                -0.455535         -0.804404                0         True   \n",
       "\n",
       "   Region_LATAM  Region_North America  Order_Priority_Low  \\\n",
       "0         False                 False                True   \n",
       "1         False                  True               False   \n",
       "2         False                 False               False   \n",
       "3          True                 False                True   \n",
       "4         False                 False               False   \n",
       "\n",
       "   Order_Priority_Medium  Payment_Method_Bitcoin  Payment_Method_Credit Card  \\\n",
       "0                  False                   False                        True   \n",
       "1                   True                   False                       False   \n",
       "2                   True                   False                       False   \n",
       "3                  False                   False                       False   \n",
       "4                   True                   False                       False   \n",
       "\n",
       "   Payment_Method_PayPal  \n",
       "0                  False  \n",
       "1                   True  \n",
       "2                   True  \n",
       "3                   True  \n",
       "4                  False  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Normalize the data using RobustScaler\n",
    "from sklearn.preprocessing import RobustScaler\n",
    "\n",
    "numeric_cols = X_reduced_no_infl_all_attribs.select_dtypes(include=['float64']).columns\n",
    "\n",
    "# Step 2: Apply RobustScaler only to the numeric columns\n",
    "scaler = RobustScaler()\n",
    "X_reduced_no_infl_all_attribs_scaled = X_reduced_no_infl_all_attribs.copy()  # Make a copy to avoid modifying the original data\n",
    "\n",
    "# Normalize only the numeric columns\n",
    "X_reduced_no_infl_all_attribs_scaled[numeric_cols] = scaler.fit_transform(X_reduced_no_infl_all_attribs[numeric_cols])\n",
    "\n",
    "# Step 3: Verify the update by displaying the first few rows\n",
    "X_reduced_no_infl_all_attribs_scaled.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "tAWrzUxpeyCQ",
    "outputId": "424b78e8-f4c0-4398-efbd-4c48bc70dd3b"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((3983, 15), (3983,))"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_reduced_no_infl_all_attribs_scaled.shape, y_reduced_no_infl_all_attribs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "PuRUO4YdymrJ"
   },
   "outputs": [],
   "source": [
    "# Split data into training and test sets\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report, roc_auc_score\n",
    "\n",
    "X_train_norm, X_test_norm, y_train_norm, y_test_norm = train_test_split(X_reduced_no_infl_all_attribs_scaled, y_reduced_no_infl_all_attribs, test_size=0.2, random_state=123)\n",
    "\n",
    "# Initialize and fit logistic regression model\n",
    "logreg_2 = LogisticRegression(max_iter=10000)\n",
    "logreg_2.fit(X_train_norm, y_train_norm)\n",
    "\n",
    "# Predict on training and test data\n",
    "y_train_pred2 = logreg_2.predict(X_train_norm)\n",
    "y_test_pred2 = logreg_2.predict(X_test_norm)\n",
    "\n",
    "# Get predicted probabilities for ROC-AUC, Precision-Recall, and Lift calculations\n",
    "y_train_prob = logreg_2.predict_proba(X_train_norm)\n",
    "y_test_prob = logreg_2.predict_proba(X_test_norm)\n",
    "\n",
    "# Get classification reports for training and test sets\n",
    "train_report = classification_report(y_train_norm, y_train_pred2, output_dict=True)\n",
    "test_report = classification_report(y_test_norm, y_test_pred2, output_dict=True)\n",
    "\n",
    "# Compute ROC-AUC scores for training and test sets\n",
    "train_roc_auc = roc_auc_score(y_train_norm, logreg_2.predict_proba(X_train_norm)[:, 1])\n",
    "test_roc_auc = roc_auc_score(y_test_norm, logreg_2.predict_proba(X_test_norm)[:, 1])\n",
    "\n",
    "# Compute confusion matrices for training and test sets\n",
    "train_conf_matrix = confusion_matrix(y_train_norm, y_train_pred2)\n",
    "test_conf_matrix = confusion_matrix(y_test_norm, y_test_pred2)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 407
    },
    "id": "3JwPBl1dsQ4M",
    "outputId": "2ba42be9-6895-44a8-fde5-a04ea840ecc1"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 600x400 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot confusion matrix for training set\n",
    "plt.figure(figsize=(6, 4))\n",
    "plt.subplot(1, 2, 1)\n",
    "sns.heatmap(train_conf_matrix, annot=True, fmt='d', cmap='Blues')\n",
    "plt.title('Confusion Matrix - Training Set')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "\n",
    "# Plot confusion matrix for test set\n",
    "plt.subplot(1, 2, 2)\n",
    "sns.heatmap(test_conf_matrix, annot=True, fmt='d', cmap='Blues')\n",
    "plt.title('Confusion Matrix - Test Set')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Ke_FK1Zky6KK",
    "outputId": "5579ac75-d7f9-4dfe-89e6-aa56c0b97cc2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification Report - Training Set:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00      1590\n",
      "           1       1.00      1.00      1.00      1596\n",
      "\n",
      "    accuracy                           1.00      3186\n",
      "   macro avg       1.00      1.00      1.00      3186\n",
      "weighted avg       1.00      1.00      1.00      3186\n",
      "\n",
      "\n",
      "Classification Report - Test Set:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00       397\n",
      "           1       1.00      1.00      1.00       400\n",
      "\n",
      "    accuracy                           1.00       797\n",
      "   macro avg       1.00      1.00      1.00       797\n",
      "weighted avg       1.00      1.00      1.00       797\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Print classification report\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "# Print the classification reports for the training and test sets\n",
    "print(\"Classification Report - Training Set:\")\n",
    "print(classification_report(y_train_norm, y_train_pred2))\n",
    "\n",
    "print(\"\\nClassification Report - Test Set:\")\n",
    "print(classification_report(y_test_norm, y_test_pred2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 626
    },
    "id": "iQwdP1lytUuA",
    "outputId": "6e195cd1-99a7-4e03-acfe-ab60305b2a15"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABjIAAAKyCAYAAAB/pUcDAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdeXhU1f0/8PdkMpmZTPYQlhBIWMK+hBBABAXqgruI2qotAoqt1N1q60Il1FarVX5aRa3fVsAVa13AulRENgUCIQQEwk6AAAkh+2zJZOb8/ogzZJkkM5NzM3fC+/U8eZTJzXvO+dw7Nzdz5p6jEUIIEBERERERERERERERqVBYsBtARERERERERERERETUGg5kEBERERERERERERGRanEgg4iIiIiIiIiIiIiIVIsDGUREREREREREREREpFocyCAiIiIiIiIiIiIiItXiQAYREREREREREREREakWBzKIiIiIiIiIiIiIiEi1OJBBRERERERERERERESqxYEMIiIiIiIiIiIiIiJSLQ5kEBERERERERERERGRanEgg4iIiIiIiIiIqAtat24dNBoNsrOzW3zvm2++waRJkxAfHw+NRoMZM2Z0evu6mh07dkCr1eL9998PdlNC2j//+U9otVr8+OOPwW4KqQgHMoiIiIiIiIiIiEJEYWEhNBoNrrjiig5lXH/99Thy5Ajmzp2LhQsX4pZbbmlz4MNXa9aswW233Ya0tDQYjUaYTCYMHToUv/nNb5CTkxNwbih4+OGHMWTIENxyyy0AgLS0NGg0Gp+/CgsLpbZn2bJl0Gg0WLZsmd8/e/z4cfz2t79Feno6DAYDoqKi0K9fP1x99dV47rnnYLFYAm6X+xieM2eO1+/Pnj0bqampePTRRwN+Dup6woPdACIiIiIiIiIiIpJv/PjxKCgoQLdu3Zo8/u2338Jut+PFF1/Ebbfd5nl83bp1AT+XzWbDHXfcgRUrViAyMhKXXnopBg0aBAA4cOAA3nvvPbz55pt4++23MWvWrICfR62+++47rFu3Dv/6178QFtbw2fEHH3wQlZWVTbZbtmwZjh07hgceeABxcXFNvtf838Gyc+dOTJ06FZWVlZg0aRKuvPJKREVF4fjx49i4cSO+/PJL3HjjjRg4cKAiz6/T6fDQQw/h/vvvxw8//IBJkyYp8jwUWjiQQURERERERERE1AVFRkZiyJAhLR4/deoUACA5OVnac915551YsWIFLrvsMrzzzjvo0aNHk+9XVlbi2WefbfHGflfx+uuvw2g04qabbvI89uCDD7bYbt26dTh27BgefPBBpKWldV4D/fDwww+jsrKy1UGnzZs3txgck+2WW27Bww8/jDfeeIMDGQSAU0sRERERERERERF1Sc2ninJP6bNw4UIAwLRp0zzTGk2dOhXTpk0DACxatMivKY/Wrl2LDz74AIMGDcJnn33WYhADaLjb4LnnnsOvf/1rz2NpaWmtvpk/depUaDSaJo9lZ2dDo9Fg3bp1WLZsGTIzMxEZGYmpU6finXfegUajwZ/+9CeveXl5edBoNPjlL3/Z5PEzZ87goYcewsCBA6HX69GtWzfceOON2L17d5t9bqyiogIrV67E9OnTERMT4/PPNSaEwFtvvYVJkyYhJiYGkZGRyMrKwltvvdViW/fdNKNHj0ZsbCxMJhPS0tLw85//HDt37gQAzJkzB3PnzgUAzJ07t8n+bM/mzZsRFxfX6p0zEydO9Hr3yK5du3DLLbegV69eiIiIQGpqKu677z6UlZV5tlm2bBn69esHAFi+fHmTdjW+IygpKQlTp07Ff/7zH5jN5nbbTF0f78ggIiIiIiIiIiI6D8TFxWHhwoVYt24d1q9fj9mzZ3sGEtyDCsuXL8eUKVMwderUJj/Xln/9618AgEceeQSRkZFtbqvX6zvSBQDA3/72N6xduxbXX389Lr/8cmi1WsycORPz58/He++9h6eeeqrFz7zzzjsA0OTN+cOHD2Pq1KkoKirC5ZdfjhkzZuDMmTP4+OOP8b///Q9r1qzBhAkT2m3Phg0b4HA4cMEFFwTUHyEEfvnLX+KDDz5Aeno6brvtNkRERGD16tW48847sXfvXrzwwgue7WfPno1///vfGDVqFObOnQu9Xo8TJ05g7dq12LZtG0aPHo0ZM2agsrISK1euxPXXX4+MjAyf25OYmIji4mKcOnXK57t2Vq1ahZ///OcICwvD9ddfjz59+mDv3r149dVX8b///Q85OTmIj49HRkYGHnjgAbz88suedro1H9SaOHEivv32W2zatAmXX365z+2nrokDGUREREREREREROeBuLg4ZGdnIzs7G+vXr8ecOXOaDFi4BzKmTp3q14LfP/zwAwDgZz/7meQWe7d+/Xrk5ORg5MiRTR6/4YYb8O6772Lr1q0YP36853Gn04kPPvgAPXv2xGWXXeZ5/Pbbb8fp06fx9ddfY/r06Z7HFyxYgKysLNx1113YtWtXu+1x93/s2LEB9eef//wnPvjgA8ydOxf/+Mc/oNPpAAB1dXW46aab8OKLL+LWW2/F2LFjUVVVhY8++ghjx45FTk4OtFptk37W1NQAQJOBjBkzZrS6sLY3P//5z7F48WJMnjwZd999Ny666CKMHj261UGqsrIyzJo1C926dcMPP/yA1NRUz/dWrFiBW2+9FU899RReeeUVZGRk4MEHH8TLL7+MjIyMNo+zrKwsAA315UAGcWopIiIiIiIiIiIiClhxcTEAICUlpVOe79e//nWLQQzg3N0W7777bpPHv/nmG5SUlOCWW27xvPG/Y8cObNq0CbNnz24yiAEAgwYNwl133YUff/zRpymmioqKAMDrlFq+ePXVV2EymbBkyRLPIAYARERE4C9/+QsA4IMPPgAAaDQaCCFgMBg8i4q7abVaKQuG/+Uvf8GcOXNw7Ngx/OEPf8CFF16ImJgYjB07Fn/+859brHPy9ttvo7q6Gs8++2yTQQygYa2LzMxMrFixwu92uOvpri+d33hHBhEREREREREREYWMxndbNHbJJZegV69eWLFiBRYvXozw8Ia3Pt0DG42nldqyZQsAoKSkxOtdAfv27fP8d8SIEW22x70GRCCDCFarFT/++COSk5Px3HPPtfi+w+Fo0p6YmBhcddVV+PLLL5GZmYmbb74ZU6dOxbhx45oMgnSEwWDA0qVL8fTTT+PLL7/E1q1bsXXrVuTl5SEvLw//+Mc/sH79evTv3x/AuVrm5OTg8OHDLfLsdjvOnj2Ls2fP+rVIeEJCAgDg7NmzEnpFoY4DGURERERERERERBSwnj17orCwECdPnvS8ua2k1u580Gq1uO222/Diiy/if//7H66++mqYzWZ89tlnGDZsGDIzMz3blpeXAwC++OILfPHFF60+l8Viabc9RqMRQMMb9v6qqKiAEAInT57EokWLfGrHRx99hGeeeQbvv/8+nnzySQANAxxz587FM8880+46Jb5KSUnBr3/9a88C7YcPH8Ydd9yBDRs24KGHHsLKlSsBnKvlkiVL2syzWCx+DWTYbDYAkNYfCm2cWoqIiIiIiIiIiIgCNmnSJADAmjVr/Pq5sLAw1NfXe/1eVVVVqz+n0Wha/V7z6aU+/vhjWK3WJndjAA1v/APAK6+8AiFEq1+zZ89utx9JSUkAzr2h7w93O8aOHdtmO9auXev5mcjISPz5z3/GkSNHcOTIEfzrX//C4MGD8fLLL+Ohhx7yuw2+GjBgAJYtWwYA+O6771r04ccff2yzD82nnWqPu57u+tL5jQMZRERERERERERE5Fk/wul0+vVzd955JwDgxRdf9HyKvjW1tbWe/4+Pj8eZM2daDGZYLBYcPHjQrza4jR49GiNHjsTKlStRU1ODd999FxqNBr/85S+bbDdhwgQAwObNmwN6nsbc63Xs37/f75+Njo7G0KFDUVBQ0GLtCV/069cPd9xxB9avX4+oqCisWrXK871A92dboqKiWjzmby19bZe7nt7WQ6HzDwcyiIiIiIiIiIiIyLMmwYkTJ/z6uWnTpuHWW2/F/v37MXPmTJw5c6bFNtXV1XjiiSfw5ptveh4bN24cHA4H3nvvPc9jQgg8/vjjPk3p1JpZs2bBZrPh73//O7777jtMmTIFffr0abLN+PHjMWHCBHzwwQf48MMPW2S4XC6sX7/ep+ebMmUKgIY1IgJx//33w2q14q677vLa76NHj6KwsBAAUFpa6nUB8oqKCtTW1sJgMHgeC3R//ulPf/L6M0II/PWvfwUATJ482fP43LlzER0djSeffBJ79uxp8XNWq9WzjgbQMICl0WjabZe7nu760vmNa2QQERERERERERGFmB9//BFz5szx+r0hQ4bgscce8ztzyJAhSE5OxooVK6DX65GSkgKNRoP77rsPsbGxbf7sv/71LwghsGLFCvTr1w+XX345Bg0aBCEEDh48iDVr1qCmpgbvvPOO52fuvfdeLF26FPPmzcPq1auRlJSEjRs3orKyEqNHj8bOnTv97gMA3HbbbXjsscewaNEiuFyuFtNKuX3wwQeYNm0abrnlFrz00kvIzMyE0WjE8ePHsXnzZpSWlvq07sWoUaPQv39/rF69OqD2/uY3v8GWLVuwfPly/PDDD7j00kuRnJyMkpIS7Nu3Dzk5OXj//feRlpaGkydPYsyYMRg9ejRGjRqF3r17o6ysDCtXroTD4cAjjzziyZ04cSKMRiNeeuklVFRUeKZoWrBgQZvtWbx4MbKzs5GVlYWxY8ciISEBZWVlWLt2LQ4cOIDExES8+OKLnu2TkpLwwQcf4Oabb8bo0aNxxRVXYMiQIaitrUVhYSHWr1+PCy+8EF9//TWAhrs6xo0bhw0bNmDWrFlIT09HWFgYZs2a5Zl+SgiBNWvWYOjQoRg0aFBAdaUuRhAREREREREREVFIOHr0qADQ5teUKVOEEEKsXbtWABALFy5skrFw4UIBQKxdu7ZF/pYtW8SUKVNEdHS0J+/o0aM+t2/16tXi1ltvFampqcJgMAiDwSDS09PFvHnzRE5OTovtv/vuOzFhwgSh1+tFYmKimDVrligpKRFTpkwRzd+6bKvdzV166aUCgDAYDKKqqqrV7crLy8WCBQvEiBEjhNFoFFFRUSI9PV3cdttt4pNPPvG5388995wA4LWPjbn75a2mH374obj00ktFfHy80Ol0onfv3mLq1KnixRdfFKWlpUIIISoqKkR2dra4+OKLRa9evURERIRITk4WV1xxhfjqq69aZH7xxRdi3Lhxwmg0evZnezZs2CAee+wxMXHiRJGcnCx0Op2IiooSo0aNEo888og4deqU15/bt2+fuPPOO0VqaqqIiIgQ8fHxYuTIkeL+++8XW7dubbLt/v37xVVXXSXi4uKERqNpsV/XrVsnAIiXXnqp3fbS+UEjhBCdOnJCRERERERERERE1IWUl5ejf//+uPnmm/F///d/wW5OyPvVr36Fr776CocPH0ZcXFywm0MqwDUyiIiIiIiIiIiIiDogISEBjz/+OJYvX45jx44Fuzkh7cCBA1ixYgUWLFjAQQzy4BoZRERERERERERERB30wAMPoLa2FsePH/es9UD+KyoqwsKFC3HPPfcEuymkIpxaioiIiIiIiIiIiIiIVItTSxERERERERERERERkWpxIIOIiIiIiIiIiIiIiFSLa2QQEREREREREXURLpcLp06dQnR0NDQaTbCbQ0RE1CohBGpqapCcnIywsLbvueBABhERERERERFRF3Hq1Cn06dMn2M0gIiLy2YkTJ5CSktLmNhzIICIiIiIiIiLqIqKjowE0vCkUExPT4byvvvoKV155ZYdzAMBmswEAjEajqrKUyGPdAqPWusnOk902QF7tWLfAsG6Bqa6uRp8+fTy/u9rCgQwiIiIiIiIioi7CPZ1UTEyMlIGMyMhIKTmNycxTa9tYt8CovW6y82Rmya4d6xYY1i0wvkyFyIEMIiIiIiIiIiJSnMw1O2Sv/6Hm9URYt8Coua+sW/CzZGPdlMeBDCIiIiIiIiIiUpxWq1VllhJ5MrFugVFzX1m34GfJxropr+2lwImIiIiIiIiIiCSoq6tDXV2d6rKUyJOJdQuMmvvKugU/SzbWTXm8I4OIiIiIiIiIiBQnc6FZmVlK5MnEugVGzX1l3YKfJRvrpjwOZBARERERERERkeKsVisAQK/XqypLiTyZWLfAqLmvrFvws2Rj3ZTHgQwiIiIiIiIiIlKcyWRSZZYSeTKxboFRc19Zt+Bnyca6KY8DGUREREREREREpDiLxQIAiIiIUFWWEnkysW6BUXNfWbfgZ8nGuimPAxlERERERERERKS4yMhIVWYpkScT6xYYNfeVdQt+lmysm/I4kEFERERERERERIqz2WwA5MzTLjNLiTyZWLfAqLmvrFvws2Rj3ZTHgQwiIiIiIiIiIlKczGlNZE+RouYpV1i3wKi5r6xb8LNkY92Ux4EMIiIiIiIiIiJSnNPpVGWWEnkysW6BUXNfWbfgZ8nGuimPAxlERERERERERKQ4IYQqs5TIk4l1C4ya+8q6BT9LNtZNeRzIICIiIiIiIiIixel0OlVmKZEnE+sWGDX3lXULfpZsrJvywoLdACIiIiIiIiIi6vrsdjvsdrvqspTIk4l1C4ya+8q6BT9LNtZNebwjg4iIiIiIiIiIFGcymVSZpUSeTKxbYNTcV9Yt+FmysW7K40AGEREREREREREpzmKxAAAiIiJUlaVEnkysW2DU3FfWLfhZsrFuyuPUUkRERERERERECnj22Wcxbtw4REdHo3v37pgxYwb279/f7s999NFHGDJkCAwGA0aOHIkvv/yyE1qrPJPJJO2TwTKzlMiTiXULjJr7yroFP0s21k15HMggIiIiIiIiIlLA+vXrcc8992DLli1YvXo1HA4HLr/8cs+nY73ZtGkTbr31Vtx5553YsWMHZsyYgRkzZmD37t2d2HJlWCyWNvserCwl8mRi3QKj5r6ybsHPko11Ux6nliIiIiIiIiIiUsDXX3/d5N/Lli1D9+7dsX37dlx88cVef+bll1/GFVdcgUcffRQA8PTTT2P16tV49dVX8cYbbyjeZiUZjUZVZimRJxPrFhg195V1C36WbKyb8nhHBhERERERERFRJ6iqqgIAJCQktLrN5s2bcemllzZ5bPr06di8ebPX7Wtra1FdXd3kS63sdjvsdrvqspTIk4l1C4ya+8q6BT9LNtZNeRohhAh2I4iIiIiIiIiIujKXy4XrrrsOlZWV+P7771vdLiIiAsuXL8ett97qeey1117DokWLUFJS0mL77OxsLFq0qMXjK1asQGRkpJR2h4Xxc7D+Yt0Cw7oFjrULDOsWGFl1s1qtuOWWW1BVVYWYmJg2t+XUUkRERERERERECrvnnnuwe/fuNgcxAvH444/j4Ycf9vy7uroaffr0wZVXXtnum0K++Pzzz3Httdd2OAcAzGYzACAqKkpVWUrksW6BUWvdZOfJbhsgr3asW2BYt8D4cxchBzKIiIiIiIiIiBR077334r///S82bNiAlJSUNrft2bNnizsvSkpK0LNnT6/b6/V66PV6aW1VksvlUmWWEnkysW6BUXNfWbfgZ8nGuimPAxlERERERERERAoQQuC+++7Dp59+inXr1qFfv37t/szEiROxZs0aPPjgg57HVq9ejYkTJyrYUu/2n92Pj4s/xt7v90rJc9Q7AAC6cJ2qspTIKyguYN0CoNa6ufN6R/XGnLFzoNFoOpSl08lpkxJkt01mHusW/Kxg4kAGEREREREREZEC7rnnHrz//vtYuXIloqOjUVxcDACIjY2F0WgEANx+++3o3bs3nn32WQDAAw88gClTpuDFF1/E1VdfjRUrViA3Nxdvvvlmp7e/oDAXa/cux0eFgDWi058+9J0KdgNClMrrlpqYip/1+1mHMtwLL7vPA2oiu20y81i34GcFEwcyiIiIiIiIiIgU8PrrrwMApk6d2uTxpUuXYs6cOQCA48ePN1kw9cILL8T777+PBQsW4IknnkB6ejo+++wzjBgxorOa7TFix0kcewmwGXV47LUbUB3fscXDXc6G6U3CtB1fIFZmlhJ5J46fQJ++faRksW6Bkd22H47/gIPlB7H15NYOD2SYTCYpbVKC7LbJzGPdgp8VTBzIICIiIiIiIiJSgBCi3W3WrVvX4rGbb74ZN998swIt8s/ApEEAAKPNgZf7/RaYMqVDeRUVFQCA+Pj4DrdNZpYSeTIXrWbdAiO7bQtXL8SfNv0JO0t2djjLYrEAACIi1Herk+y2ycxj3YKfFUwcyCAiIiIiIiIiopZmzEBNnz6IPnFCSpyaP2Gs5k8ss26Bkd22rJQsAMDO4o4PZJxPdVPz8SsT66Y8DmQQEREREREREVHbfLi7pD1q/oSxmj+xzLoFRnbbBkYPBADsL9sPm8MGoy7w9QbOp7qp+fiViXVTHgcyiIiIiIiIiIhIcTIXmpW9aK2aF8Fl3QIju21piWlIikxCqbUUu8/sxrje4wLOOp/qpubjVybWTXlyVrshIiIiIiIiIiJqQ21tLWpra1WXpUSeTKxbYGS3ra6uDsO7DQeADq+TcT7VTc3Hr0ysm/I4kEFERERERERERG2TMLWUVquFVquV0Bi5WUrkycS6BUaJvo5MGgmg4+tknG91U+vxKxPrpjwOZBARERERERERkVdCowl2E4hUY2T3nwYyOnhHBhH5j2tkEBERERERERGR4pxOpyqzlMiTiXULjBJ9HZYwDACwq2QXhBDQBDjQd77VTY1ZsrFuyuNABhERERERERERtU3C1FJ6vV5CQ+RnKZEnE+sWGCX6OrLXSOjCdKiqrcKxqmNIi0tTRdtkUvMxwroFPyuYOLUUERERERERERF5J3FqKZvNBpvNprosJfJkYt0Co0RfnXVODO/+04LfHVgn43yrm1qPX5lYN+XxjgwiIiIiIiIiIlKcyWRSZZYSeTKxboFRqq+je4xGfnE+8ovzcf2Q6zuUpUZqPkZYt+BnBRMHMoiIiIiIiIiIqG0SppayWCwAgIiICFVlKZEnE+sWGKX6OrrHaAAdW/D7fKybGo9fmVg35XEgg4iIiIiIiIiIFKfmTxir+RPLrFtgFLsjo2fHBzLOx7qpLUs21k15HMggIiIiIiIiIiLFqfkTxmr+xDLrFhil78g4UnEE1bXViNHHBL1tMqn5GGHdgp8VTBzIICIiIiIiIiKitkmYWspgMEhoiPwsJfJkYt0Co1RfjUYjekf3xsmak/ix5EdM6jsp6G2TSc3HCOsW/KxgCgt2A4iIiIiIiIiISJ2ERiMty+FwwOFwqC5LiTyZWLfAKNnXjk4vdb7WTU1ZsrFuyuNABhERERERERERKS4sLAxhYXLeipKZpUSeTKxbYJTsq2fB7+LABjLO17qpKUs21k15nFqKiIiIiIiIiIjaJmFqKY3EuztkZimRJxPrFhgl++oZyAjwjozztW5qypKNdVMeBzKIiIiIiIiIiMg7yVNLqTFLiTyZWLfAKNnXjJ4ZAIBdJbvgdDmhDdMGnKU2aj5GWLfgZwUTBzKIiIiIiIiIiEhxal68Vs2L4bJugVGyrwMTBsIYboSt3oZD5YcwuNvgoLZNJjUfI6xb8LOCKfQnxyIiIiIiIiIiImVJmFrKZrPBZrNJaIzcLCXyZGLdAqNkX7VhWozsMRJAYNNLna91U1OWbKyb8nhHBhERERERERFRF+N+00qj0UCr1aKurg5GoxFWqxUmkwkWiwWRkZGw2WyIiIiA0+mEEAI6nQ52u92zjfsTsHV1dbBWVkKn00EIAZfL1WJb93+NRiNqa2uh1TZMt+N0OqHX6+FwOBAZGYmKigrPtgaDAQ6HA2FhYdBoNHA4HDAYDLDZbC1y3dtqNBqEhYWhrq4OtbW1fvepcTvtdjt0Oh0AwOVywWaz+dWn1tophIDZbParT63tJ51OB5vNBqvV6lefvO2nxvvA3z55209t7dNAjj0hBOrq6vzqU3v7yW63+9Wn1rZ1uVzQaDSwWq2oq6vDiG4jsPXkVuSdysNlyZf5deyFh4fDbrfDYrEE/Hpq3k4hBGw2W0Cvp8b7qfE+DfT11LhP3o6Rjh577e1Tf4+9tl73vh577uczm80Bv54ab6vT6WC1Wj37tCPn8uav+468ntx9EkJIOZdbrVaff6/xjgwiIiIiIiIiohC3ZMkSDBs2DOPGjQt2U1plt9v9etOqLe43+GSRnSeTzLbJ3AdK5Mmk9CfkR3UfBaBhnQx/Wa1W2O12aW2TSc3HiJrrpsQ5SVZf1fw69YdGCAn3BhIRERERERERUdBVV1cjNjYWVVVViImJ6XBeVf/+iD16FPj6a2D69A5l1dXVAQAiIiI63C6ZWUrkff7557j22mulZLFugVG6r98f/x4XLb0IKTEpOPHQiaC2DZBXOzUfI6xb8LPcZNXNn99ZnFqKiIiIiIiIiIi802ikRVksFgBy3kyTmaVEnkysW2CU7uuoHg13ZBRVF6HMWobEyMSgtU0mNR8jrFvws4KJAxlERERERERERKQ4g8Ggyiwl8mRi3QKjdF9j9DHoH98fRyqOIL84H5f0vyRobZNJzccI6xb8rGDiGhlERERERERERNQ2CTOTOxwOOBwOCY2Rm6VEnkysW2A6o69jeo4BAOwo3hHUtsmk5mOEdQt+VjBxIIOIiIiIiIiIiLwSEqeW0mg00EjKk5mlRJ5MrFtgOqOvmb0yAQB5p/OC2jaZ1HyMsG7BzwomTi1FRERERERERERtk3BHhlarldAQ+VlK5MnEugWmM/oa6B0Z53vd1JAlG+umPN6RQURERERERERE3kn8FG9dXR3q6upUl6VEnkysW2A6o6/uOzL2n90Pc505aG2TSc3HCOsW/Kxg4h0ZRERERERERESkOKPRqMosJfJkYt0C0xl97RHVA72ieuG0+TR2lezChX0uDErbZFLzMcK6BT8rmHhHBhERERERERERtU3C1FJWqxVWq1VCY+RmKZEnE+sWmM7qayDrZLBuwc+SjXVTHu/IICIiIiIiIiIixZlMJlVmKZEnE+sWmM7q65ieY/DFwS+w47Tv62SwbsHPko11Ux4HMoiIiIiIiIiISHEWiwUAEBERoaosJfJkYt0C01l99dyRUez7HRmsW/CzZGPdlMeppYgo6D777DNoNBps2rQp2E0JaQsWLEB0dDRKSkqC3RQiItVbtmwZNBoNli1bFtDPT506FRqJi5+e7+bMmQONRoPCwkLPY4WFhdBoNJgzZ07Q2hWKeF0lB6+riLyQMLVUZGQkIiMjJTRGbpYSeTKxboHprL6O6TUGALDnzB7U1tcGpW0yqfkYYd2CnxVMHMigkOX+47bxl06nQ+/evfHzn/8cubm5bf58VVUVnn76aYwbNw5xcXEwGAzo168fZs+ejby89kfR16xZg9tuuw1paWkwGo0wmUwYOnQofvOb3yAnJ8evvggh8Mknn2DmzJlISUmBXq9HdHQ0Ro8ejYceegh79+71Ky+UOBwO/P73v8f06dNx4YUNi2I136/tfcmWnZ0NjUaDdevW+f2zu3fvxuzZs5GWlga9Xo/Y2FgMHDgQM2fOxMsvvwzRgYv/devWQaPRIDs72+v3f/e73yEsLAwLFy4M+DmIiDrK2+/niIgI9OnTB7fddht27doV7CZ2WWlpaU3qrtVqkZiYiEsuuQQfffRRsJvXaXhdxesqX/C6ish3QuK5wWazwWazqS5LiTyZWLfAdFZfU2NTEW+Ih8PlwJ7SPUFpm0xqPkZYt+BnBROnlqKQN2DAAPzqV78C0HCr1Pbt2/HRRx/hs88+w7fffouLL764xc9s27YN1113HYqLizFixAjcfvvtiIyMREFBAVasWIF33nkHCxcu9PqHi81mwx133IEVK1YgMjISl156KQYNGgQAOHDgAN577z28+eabePvttzFr1qx2219eXo6bb74Z3333HeLi4nDZZZehf//+qKurw549e/Daa6/h73//O9asWYOpU6d2rFgq9M477+DgwYN44403PI95q/tLL72EqqoqVf8xuXr1alxzzTWor6/HpZdeihtuuAEGgwGHDx/G+vXr8emnn+Kee+5BeLgyp974+HjMmzcPL7/8Mh5//HGkpqYq8jxERL5o/PvZbDZjy5Yt+OCDD/DJJ59gzZo1mDRpUlDbd8MNN+CCCy5Ar169Avr5t99+W5UL5mm1WixYsABAw5vahw4dwqefforvvvsOzzzzDB5//PEgt1BZvK7idZUsvK4iUobMaU1kT5Gi5ilXWLfAdFZfNRoNxvQag++Ofocdp3d4pprqzLbJpOZjhHULflYwcSCDQt7AgQNbfJLqr3/9Kx5//HH88Y9/xPr165t87/jx47jiiitQWVmJ119/HXfffXeT7+/fvx9XX301srOzkZSUhN/+9rdNvn/nnXdixYoVuOyyy/DOO++gR48eTb5fWVmJZ599FpWVle22vb6+HjfccAM2bNiAX/3qV1iyZAliYmKabHP69Gk8+eSTqKqqajcvFL3++uvo06cPpk2b5nnM2yfjli1bhqqqqlY/NacG8+fPh9PpxLffftukP0DDp0O/+eYbaLVaRdvwq1/9CosXL8Y///lPPP3004o+FxFRW7z9fl6wYAH+8pe/4Mknnwzo09kyxcbGIjY2NuCf79u3r8TWyBMeHt6i7j/88AMuvvhiPP3003jggQe6xG3l3vC6itdVsvG6iqgZCVNLOZ1OCQ2Rn6VEnkysW2A6s6+ZPTPx3dHvkHc6D3fizg5lBZuajxHWLfhZwcSppahLuvPOhl8a27dvb/G9J554AuXl5Xj88cdbDGIAwODBg7Fy5UrodDo8/vjjTf7QXbt2LT744AMMGjQIn332WYtBDACIi4vDc889h1//+tfttvOdd97Bhg0bcPHFF2P58uUt/tgGgF69euGtt97CFVdc4XlMo9G0+inCtLQ0pKWlNXnMPe/0kSNH8OKLL2LYsGHQ6/WYM2cOnn76aWg0Grz99tte8z755BNoNBo8+eSTTR4/evQo5s2bh759+0Kv16NXr16YM2cOjh071m6/3Xbv3o3c3FzceOONAU9lUFdXh8WLFyMzMxMmkwnR0dG46KKLsGrVqhbbVlVV4amnnsKwYcMQFRWFmJgYDBw4ELNnz/a0e+rUqVi0aBEAYNq0aZ5pFprXtLkzZ87g8OHDGDFiRIs/toGGfTZ9+nSv/dywYQOuvfZadOvWDXq9Hunp6ViwYEGTT/pmZ2d7chctWtRkCojG84mPGTMGAwcODHjOdyIiJd13330AGu6MdHP/Tjt58iRuv/129OzZE2FhYU0GOnw5Tza2YcMGzJgxAz169IBer0efPn0wc+ZMfP/9955tWlsjIy8vDzfddJPn91tSUhLGjRuHv/zlL022a22NjPr6eixevBijR4+G0WhEbGwspk2bhs8//7zFto3b8M033+DCCy9EZGQkEhMTMXv2bJSVlbVbU19MmjQJQ4YMgc1m8zqt0sqVK3HJJZcgPj4eBoMBI0aMwAsvvNDqHzwrV67E5ZdfjsTERBgMBqSlpWHWrFnYvXu3Z5sDBw7g97//PTIzMz3bDRo0CI899hjMZrOUfjXH6ypeVwG8riJShMSppYQQHZoWTqksJfJkYt0C05l9da+TsaN4R1DaJpOajxHWLfhZwcQ7MqhLa36rucViwb///W8YDAY88sgjrf7c8OHDMXPmTHz44Yf46KOPMG/ePADAv/71LwDAI4880u6nGfV6fbvtc+ctWLAAYWFtjyv6ktee++67D1u2bMHVV1+Na6+9Ft27d8fMmTOxcOFCvPvuu7j99ttb/Mw777wDAE2mycrJycH06dNhsVhwzTXXID09HYWFhXjvvffw1VdfYfPmzejfv3+77VmzZg0A4IILLgioP7W1tbjiiiuwbt06ZGRk4M4774TD4cAXX3yB66+/Hq+88gruvfdeAA0n7enTpyMnJweTJk3CFVdcgbCwMBw7dgyrVq3CrFmzkJqa6llQdP369Z45mYGGAaq2xMbGIjw8HKdPn4bFYoHJZPKpD6+//jruuecexMXFefZJbm4u/vKXv2Dt2rVYu3YtIiIiMHXqVBQWFmL58uWYMmVKkzdcmrdt4sSJeOedd3DgwAHPtGdERGrS/M3HsrIyTJw4EQkJCbjllltgt9s9b0L7ep50e/nll/HQQw/BaDTihhtuQN++fXHy5El8//33+M9//oPJkye32q78/HxceOGF0Gq1uP7665GamorKykrs3bsXb775Zos3n5sTQuCmm27CypUrMWjQINxzzz2wWCz48MMPcd1112Hx4sV46KGHWvzcqlWr8MUXX+Daa6/FhRdeiA0bNuDtt9/G4cOHmwy+yND82ujxxx/HX//6V/Tu3RszZ85EbGwsNm7ciEcffRQ5OTkt1tb43e9+h8WLFyMhIQEzZsxA9+7dceLECXz77bcYO3YsRowYAaDhDft//etfmDZtGqZOnQqXy4UtW7bgueeew/r167FhwwbodDqpfeN1Fa+reF1FpH4yz/2yf4/IzpOJdQtMZ/bVPZ1UfnE+nC4ntGFt3zXIugU/SzbWrRMIohB19OhRAUBMnz69xfeeeeYZAUBcffXVTR5ft26dACAmTZrUbv6bb74pAIg77rjD81haWpoAIA4dOtTh9jscDqHT6UR4eLiw2Wx+/SwAMWXKFK/fS01NFampqU0emz17tgAgUlJSxLFjx1r8zOTJk4VWqxWnTp1q8nhZWZmIiIgQWVlZnsfq6upEWlqaiI6OFnl5eU2237hxo9BqteKaa67xqR8333yzACAOHjzY7rapqami+SnriSeeEADEH//4R+FyuTyPV1dXi6ysLBERESFOnjwphBBi165dAoCYMWNGi2y73S5qamo8/164cKEAINauXetTP9xmzpwpAIiRI0eKv//97yI3N1fU1ta2uv2ePXtEeHi4GD16tDh79myT7z377LMCgHjhhRc8j61du1YAEAsXLmyzHS+//LIAIN566y2/2k9EJENbv5+feuopAUBMmzbN8xgAAUDMnTtX1NfXN9ne3/Nkfn6+CAsLE8nJyeLo0aNNtne5XJ7fCUIIsXTpUgFALF261PPYww8/LACIzz77rEXbmz//lClTWvxeWr58ued3dOPz/7Fjx0S3bt1EeHi4OHz4cIs2hIeHi++//97zeH19vZg6daoAIDZv3tyiLa1JTU0Ver2+xePff/+9CAsLE4mJiU2uOb755hvPvjKbzZ7HXS6XuPvuuwUA8Z///Mfz+Oeff+75Pde8Hg6HQxQXF3v+XVRU5PV34KJFiwQA8e677zZ53H2t0ni/uY+l2bNnt9t3XlfxuorXVUTnVFVVCQCiqqpKSl75oEFCAEKsWtXxrPJyUV5eLqFVcrOUyFsloV5urFtgOrOv9c56EfmXSIFsiD1n9nR624SQVzs1HyOsW/Cz3GTVzZ/fWZxaikLeoUOHkJ2djezsbDz66KP42c9+hieeeAI9evTA3/72tybbFhcXAwD69OnTbq57m9OnT7f4+ZSUlA63u6ysDA6HA926dYPBYOhwni8effRRr3N6z5o1C06nEx988EGTxz/88EPU1dV5FmsFgP/+978oLCzEo48+ijFjxjTZfvLkybj++uvx5Zdforq6ut32FBUVAYDXKbra43K58Prrr2PAgAGeKQHcoqOj8dRTT6Gurg6ffPJJk58zGo0tsvR6PaKiovxuQ3Nvvvkmrr32Wvz444+4//77kZWVhejoaEyaNAl///vfYbPZmmz/j3/8A/X19XjllVeQmJjY5Hu///3vkZSU1GKf+MJdT3d9iYiCofnv54svvhh/+tOfYDAYWkzTFBERgeeff77FfPf+nif/8Y9/wOVy4c9//nOLqWs0Gg2Sk5N9aru33xXNn9+b5cuXAwCef/75JneJ9O3bFw899BDq6+vx3nvvtfi52267rcni51qtFrNnzwbQdBouX9TX13vq/uSTT+IXv/gFpk2bhrCwMLz22mtNrjleffVVAA2/vxp/4l2j0eCvf/0rNBpNk/q+9tprABruemlej/Dw8Ca/z3v37u11UUH3J/q//fZbv/rVHl5X8bqK11VEocFkMvl8l1VnZimRJxPrFpjO7Ks2TIuMnhkAgB2n259einULfpZsrJvyOLUUhbzDhw975t5169mzJzZu3IiBAwcGqVXqNH78eK+P//znP8f999+Pd955Bw8//LDn8XfffRfh4eG49dZbPY9t2bIFQMOi6N4WiCwuLobL5cKBAweQlZXVZnvKysqg1WoRHR3td1/279+PiooKJCcnt9j/AFBaWgoA2LdvHwBg6NChGDVqFD744AMUFRVhxowZmDp1KjIyMtqdfsJXiYmJWLVqFQ4ePIivv/4aW7duxZYtW7Bp0yZs2rQJ//d//4f169cjISEBwLla/u9///NMB9GYTqfztN8f7vyzZ892oDdERB3T+PezTqdDjx49cNttt+Gxxx7DyJEjm2zbr18/dOvWrUWGv+fJrVu3AgAuv/zygNr885//HC+99BJuuOEG/OIXv8Bll12Giy++GL179/bp53fs2IHIyEivv2/d8/Hn5+e3+N7YsWNbPOb+0ERlZaXnsZdeeqnJv4GG9RoaD9o4nc4WvxfDw8Px0UcfYcaMGU0e37JlC0wmE9566y2v/TEajS3qq9frMWXKFK/bNyaEwNKlS7Fs2TLs3r0bVVVVcLlcnu+fOnWq3Qy143UVr6uIyH8WiwUAvA52BzNLiTyZWLfAdHZfx/Qcg00nNiHvdB5+OeqXndo2mdR8jLBuwc8KJg5kUMibPn06vv76awANf2QtX74cf/jDH3Dddddh69atTT4R1rNnTwDAiRMn2s11b9OrV68mP19YWIiTJ0/6NFdxWxITE6HT6VBWVoba2lopczW3p7VP6MXFxeGaa67Bxx9/jL1792LYsGE4fPgwNm3ahKuuugrdu3f3bFteXg4AXj9R2pj7JNkWo9EIp9MJh8Ph93x97nbs2bMHe/bsabcd4eHh+O6775CdnY2PP/4Yv/vd7wAASUlJuPfee/Hkk0+2+CRwoNLT05Genu75d35+Pn71q19h9+7dWLRoEV5++eUmfWj+yeSOcn9Csb11XIiIlNT493N7Wvv95O95sqqqChqNpsnvbn9MmDAB69atwzPPPIP3338fS5cuBQCMGzcOzz33nNdFhxurrq5u9a5Pd5u8fbLe26LU7rUsGi+4/dJLL7VY/Hnq1KlNBjL0ej3sdjsAwGw247vvvsMdd9yBWbNm4fvvv8fo0aM925aXl6O+vt7rG9dujX+fV1VVoXfv3j69UX3//ffj1VdfRZ8+fXDdddehV69enmudRYsWoba2tt0Mf/C6itdVvK4i6gQSFoqV/WllmdT8aWXWLTCd3Vf3Ohm+LPjNugU/SzbWTXmcWoq6lKSkJDzyyCN44oknUFBQgAULFjT5flZWFnQ6HbZv346qqqo2s9yf5Jo4caLnMfe0D94+5eWv8PBwjB8/Hg6HAxs2bPDrZzUaDerr671+r61+NV9ctTH3opPuRSjffffdJo+7ud9s+fzzzyGEaPXLl09rJiUlATj3h6c/3O248cYb22yH+00ooOFNjldeeQUnT57E3r178eqrryIhIQELFy7E888/73cbfJWRkYFXXnkFAPDdd9+16EN1dXWbffCXu57u+hIRqV1rv5/8PU/GxcVBCNFkWkh/XXTRRfjqq69QUVGBtWvX4uGHH8aPP/6Iq6++GkeOHGnzZ2NiYnDmzBmv33NPT+lt0MJXhYWFLfreeJHi5qKionDdddfhww8/hNlsxty5c5vUKyYmBomJiW3W9ujRo57t4+LiPHcItOXMmTNYsmQJRo0ahX379mHZsmV49tlnkZ2djbvvvjvg/reF11W8ruJ1FZFyRBvnO39ZLBafBmc7O0uJPJlYt8B0dl/H9GyYJnJH8Y52f+ewbsHPko11Ux4HMqhLeuKJJ5CcnIzXXnsNhYWFnsdNJhNuvvlm2O12vPjii63+fEFBAT799FNER0fjpptu8jx+5513AgBefPHFFvPyNufLJw3dec8880y7v+Qa58XHx+PkyZMttiksLGwx5YSvrrrqKiQmJuL999+Hy+XCe++9h+joaFx//fVNtpswYQIAYPPmzQE9T2PuqUX279/v988OHToUMTExyM3NhcPh8OtnNRoNhg4dinvuuQerV68GAKxatcrzffcnCBt/CrajvM0V7a6leyqE9vjaLnc9m0/dQkQUavw9T7qn+vnmm286/NxGoxFTp07Fiy++iCeeeAI2m83zO6M1Y8aMgdVq9Uxx1di6desANLwJ29kuueQSzJgxAzt27GiyRsCECRNQVlaGgwcP+pQzfvx41NbWYv369W1ud+TIEQghcOmll7b4FPvGjRv974CPeF3F6yqA11VEamc0Gr2urxPsLCXyZGLdAtPZfR3efTh0YTpU2itRWFnYqW2TSc3HCOsW/Kxg4kAGdUlGoxF/+MMf4HA48PTTTzf53jPPPIP4+Hg888wz+Oc//9niZw8ePIjrr78edXV1+Otf/4q4uDjP96ZNm4Zbb70V+/fvx8yZM71+6rK6uhpPPPEE3nzzzXbbOWvWLFx00UVYt24d5s6di5qamhbblJSU4K677moyPce4ceNQWFjY5I2Eurq6JvMw+0un0+EXv/gFjh8/jueffx4HDx7EjTfe2OJEd/3116Nv375YvHix1088OhwOfP/99z49p/vThTk5OX63Nzw8HPPnz8exY8fwyCOPeP2je/fu3Z59VFhY2GRQy62kpAQAmiwM6p4L2ZcpyNwsFgv+8pe/eJ0/ub6+3rPw/OTJkz2P//a3v0V4eDjuu+8+HD9+vMXPVVZWYseOc7ek+tqunJwchIeH48ILL/S5/UREauTvefLuu++GVqvFggULWkzBJIRod12GzZs3e6Zlaszb7wpv3At0P/74401+L504cQKLFy9GeHg4fvnLtudLVkp2djY0Gg0WLVrkeeP2/vvvBwDccccdKCsra/EzxcXFKCgo8Pz7nnvuAQA88MADLT71X19f76lTamoqAGDTpk1N7t4oKirC448/LrFXTfG6itdVvK4iUpiEqaXsdrvX37XBzlIiTybWLTCd3dcIbQRGdB8BAMg7ndepbZNJzccI6xb8rGDiGhnUZf3617/Gc889h7fffhtPPPEEBgwYAKDhj+svv/wS119/Pe666y688sormDp1KiIjI1FQUICvvvoKDocD2dnZ+O1vf9si91//+heEEFixYgX69euHyy+/HIMGDYIQAgcPHsSaNWtQU1PjmUqgLeHh4fjss89w8803Y/ny5Vi1ahUuv/xy9OvXD3V1ddi7dy/WrVsHh8OBX/3qV56fe/jhh/HNN9/gqquuwq233orIyEisXr0acXFxAc8LDjS8AfDaa6/hqaee8vy7Ob1ej//85z+48sorMWXKFPzsZz/DyJEjodFocOzYMWzcuBGJiYk+LaZ4ySWXIDo6GqtXr8ajjz7qd3sXLVqEvLw8/P3vf8cXX3yBiy++GN27d8fJkyfx448/YufOndi8eTO6d++O/Px8zJw5E+PHj8ewYcPQs2dPnDx5Ep999hnCwsLw0EMPeXKnTZsGjUaDJ554Anv27EFsbCzi4uJw7733ttoWh8OBBQsWIDs7GxMnTsTo0aMRExODkpIS/O9//0NRURH69euHhQsXen5mxIgReO211zB//nwMHjwYV111FQYMGICamhocOXIE69evx5w5c/DGG28AAIYMGYLk5GSsWLECer0eKSkp0Gg0uO+++xAbGwugYT70LVu24LLLLusycyAS0fnL3/PkyJEj8dJLL+H+++/H8OHDMWPGDKSmpqK4uBgbNmzA1VdfjZdeeqnV53vuueewdu1aXHzxxejXrx8MBgPy8vKwZs0a9O/fHzfccEOb7Z01axY++eQTrFy5EqNGjcI111wDi8WCDz/8EOXl5XjxxRc7vMZWoEaPHo0bbrgBn3zyCd59913Mnj0bV1xxBf74xz/i6aefxsCBA3HFFVcgNTUVZWVlOHToEDZu3Ig///nPGDp0KICGuwweeeQRvPDCC0hPT8cNN9zg+b27Zs0aPPLII3jwwQfRq1cv3Hjjjfj444+RlZWFSy65BCUlJfjvf/+LSy65BIcPH1akj7yu4nUVr6uIFCJxail/1/DprCwl8mRi3QITjL5m9srEjuId2FG8AzcOu7FDWcGi5mOEdQt+VlAJohB19OhRAUBMnz691W1eeeUVAUDMmjWrxffKy8tFdna2yMzMFDExMSIiIkL07dtX3H777SI3N7fd51+9erW49dZbRWpqqjAYDMJgMIj09HQxb948kZOT41dfXC6X+M9//iNmzJghkpOTRUREhIiMjBQjRowQ999/v9i7d2+Ln/noo4/EyJEjRUREhOjZs6e47777RE1NjUhNTRWpqalNtp09e7YAII4ePdpuW9LT0wUAkZKSIpxOZ6vbFRUViQceeECkp6cLvV4vYmJixNChQ8W8efPEmjVrfO77/PnzhVarFadOnWpzu9TUVOHtlFVfXy/+8Y9/iEmTJomYmBih1+tF3759xRVXXCFef/11YTabhRBCnDhxQjz22GPiggsuEN27d/fs75kzZ4rNmze3yF22bJkYOXKk0Ov1AkCLmjbndDrFl19+KR544AExduxY0aNHDxEeHi5iYmJEVlaWWLRokaisrPT6s1u3bhW33HKLSE5OFjqdTnTr1k1kZmaKxx57TBQUFDTZdsuWLWLKlCkiOjpaAGixX5ctWyYAiM8++6zN9hIRKcWX38+NARBTpkxpcxt/zpNCCLF27VpxzTXXiISEBBERESFSUlLEjTfeKH744QfPNkuXLhUAxNKlSz2Pff311+L2228XgwcPFtHR0SIqKkoMGzZMPPHEE6K0tLTJc0yZMsXr7yWHwyFeeOEFz++Q6OhoMWXKFLFy5coW23prQ+M+ABALFy5sszaNpaamCr1e3+r3d+7cKTQajejfv79wOByex1evXi2uvfZakZSUJHQ6nejZs6eYOHGiePrpp8Xx48db5Hz88cdi2rRpIjY2Vuj1epGWliZmzZoldu/e7dmmpqZG/O53vxNpaWlCr9eL9PR08fTTT4u6ujqv+9zbtYr7WJo9e7bPNRCC11W8ruJ1FVFVVZUAIIqLi0VVVZWorq4WFotFVFRUCLvdLsrLy0Vtba0oLy8XdrtdVFRUCIvFIqqrq0VVVZWwWq1NtikbPFgIQNT++9+ioqJCmM1mUVNT43Vb939tNpuorKwUNTU1oqamRlRWVgqbzSZOnjwpysvLm2xrtVpFVVWVqKmpEWazWVRUVAibzeY1171tdXW1OHPmjDh58mRAfWrcTnefSkpKxOnTp/3uU2vtXLlypd99am0/lZWViZMnT/rdJ2/7qfE+8LdP3vZTW/s0kGNv5cqVfveptf1UUlIiTp065XefWtv29OnTori4uM0+Pb/ueYFsiMuWXdZmO8+ePStOnTrVoddT821XrlwZ8OupcZ8a79NAX0+N++TtGAn02Dtz5oxP+9SfY89dt0BeT972aUdeT423KS8vFydPnuzQ66m1131Hz+Xl5eVi5cqVUs7lp0+fFgBEVVVVu7/fNEJIuDeQiChA+/fvx4gRI5CdnY0nn3wy2M0JeRdddBFKSkpQUFDgmfuZiIiIzg+8rpKL11UUapYsWYIlS5bA6XTiwIEDKC4uhtFohEajgVarRV1dHYxGI6xWK0wmEywWCyIjI2Gz2RAREQGn0wkhBHQ6Hex2u2cbMXEiEvbvR92HH8J6+eXQ6XQQQsDlcrXY1v1fo9GI2traJuvR6PV6nD17FkajEWFhYZ5tDQYDHA4HwsLCoNFo4HA4YDAYYLPZWuS6t9VoNLDZbHA4HOjWrZvffWrcTrvdDp1Oh5qaGrhcLsTHx/vVp9bauXr1avzsZz/zq0+t7Sen04na2lrEx8f71Sdv++nMmTOefeBvn7ztp7b2aSDH3urVq3HFFVf41afW9pPZbIbL5UJCQoJffWptW/faWbGxsa32af2R9Zj+7+noYeqBA78+0Go73fs0Li4u4NdT83Z+/fXXuOyyywJ6PTXeT6WlpZ59GujrqXGfysrKWhwjgR57FosF9fX1SExMDPj11LxPa9euxWWXXRbQ66nxtvX19XA4HIiJiQn49dR4W5fLBZvNhsTExIBfT6297gN5PTXv08aNG3HRRRd1+FxusVjQq1cvVFVVeWrXGg5kEFHQzZ8/Hx999BGOHj2K6OjoYDcnZK1ZswaXXnopPvnkk3anPyEiIqKuiddVcvC6ikJZdXU1YmNjfXpTyBflQ4ciYd8+4NNPgRkzOpRls9kAQMqiszKzlMj7/PPPce2110rJYt0CE4y+WuosiPlrDFzChZMPn0RydHKntA2QVzs1HyOsW/Cz3GTVzZ/fWVzsm4iCbtGiRbj33nu9LhpJvquqqsILL7zAP7aJiIjOY7yukoPXVUTKUPPitWpeDJd1C0ww+mqKMGFot4b1xbaf2t5pbZNJzccI6xb8rGDiYt9EFHTdu3dHdnZ2sJsR8mbOnBnsJhAREVGQ8bpKDl5XEXkhYUIPk8kkoSHys5TIk4l1C0yw+pqVnIU9pXuQeyoX1w72/ol11i34WbKxbsrjHRlEREREREREROSdRiMtymKxwGKxqC5LiTyZWLfABKuvWclZAIDc07md1jaZ1HyMsG7Bzwom3pFBRERERERERESKU/MnjNX8iWXWLTDBvCMDAHJP5UIIAY2XwUDWLfhZsrFuyjvvBjJcLhdOnTqF6OhorycSIiIitRBCoKamBsnJyQgL402UoYrXHkREFCp47UFtkjC1lPsTwREREarKUiJPJtYtMMHq6+geo6HVaHHGcgZF1UXoE9tH8bbJpOZjhHULflYwBXUgY8OGDfjb3/6G7du34/Tp0/j0008xY8aMNn9m3bp1ePjhh7Fnzx706dMHCxYswJw5c3x+zlOnTqFPn5YnECIiIrU6ceIEUlJSgt2MLoHXHkRERO3jtQc1JiR+EMNoNKoyS4k8mVi3wASrr0adEcO7D8eukl3Yfnq714EM1i34WbKxbsoL6kCGxWLB6NGjcccdd/i0mNrRo0dx9dVX4+6778Z7772HNWvWYN68eejVqxemT5/u03NGR0cDaLgwi4mJAQDk5uYiKysr8I60QolcZjKTmcxk5vmTWV1djT59+nh+d1HHdeVrD17PMJOZzGQmMzuayWsPUlptbS0AwGAwqCpLiTyZWLfABLOvWb2ysKtkF3JP5WLGkBmKt00mNR8jrFvws4IpqAMZV155Ja688kqft3/jjTfQr18/vPjiiwCAoUOH4vvvv8f/+3//z+c3E9xTOsTExHjeTDCZTJ7/l0mJXGYyk5nMZOb5l8npiOTpytcevJ5hJjOZyUxmysrktQd5JWFqKa1WK6Eh8rOUyJOJdQtMMPualZyFt/LfQu4p7wt+s27Bz5KNdVNeSK2RsXnzZlx66aVNHps+fToefPDBgDOFEIhJjIGlTv7K7UrkMpOZzGQmM7tmpsvpRMWpU4g1hkO4XNBwXmpVUOLaY+9Xb6Ni03fYtOE91BsiUHzhKLj0HZ+rtNRaiqO7j3Y4pzNymclMZjKTmerJjI2IlZpHRES+LfhNRP4JqYGM4uJi9OjRo8ljPXr0QHV1NWw2m9f5vmpraz23zwANt8q6CSEweelkbDqxSblGExERtccFaD8D+u8C1gGwlpfAFN89yI0iQP61BwCcfeU5XPHVXs+//zgN+PMUyQ0nIiLyUXhYOE4PPo1ukd2C3RRSOwl3ZDidTgkNkZ+lRJ5MrFtggtnXUT1GQRemQ5mtDMeqjiEtLk3Rtsmk5mOEdQt+VjCF1EBGIJ599lksWrSoxeO5ubkI04dxEIOIiDqfACIdP/2vAOq+AJy7gIMALgPw+ZkSaKttOHz4cDBbSQFq69rDZDLBmT4QOYeOI6WsDr3L65CFZGQlJANomLNUQKDW3jAQEhUdBZvVBqfTCa1WC2OkEeYaMwBAb9BDAw3sdjsAQEAgPDwcznonwsLCYIoyoaa6BgAQoY+ANkwLm80GADBFmVBrr0V9fT00YRpER0V7Blwi9BHQarWwWRu2FUJAF6FDvaMeGo0G0TE/bSsAXYQOunAdrFYrACAyMhKOegccdQ5A0zCdlmdbnQ66CB2sFisc9Q7ExMTAWe9EXV0dACAmNgY1NTUQLoFwXTj0ej0s5oY7noxGI5wuJ+pqG7aNjomGxWyBy+VCeHg49AY9KisroQvXwWA0QIhzNYyOjobFaoHL6WpRQ/ccse4aNq53mDYMTqcTGmjO1Vujgd1mb1FDn+pdW4t6Rz3q6+uRkJiA6qqf6h0RAW34uXpHmiLhqHPA4fBSw1bqbbVaodPpEBMTg5rqGgjRUMOIiAhYLQ3bGiONcDrP1TAmJgY15p/q/VMNG9fbbDFDG6ZtUW9tuBZGgxFm87ka+nrMulwuREZGnqt3VBRsdlvDMasNgynShJqahhrq9Xpowlqvd1RUFKqrq+God8BkMjWtt8mE2rqGemvCNIiOjvbUWxehQ3h4eNN6O5oes+Vl5QgPD2+ot07XpIb19fUN23o7ZiP0sFi8H7MCAtowbZNj1l1vg9EA4RKeAdAmx2wb9XbUOxAfH+/zOaJJvVs5ZqtrqqEL1/l1jog0RaKurq7Vc0RtbS3CNGF+nSM8x2wr5win04mY2Bi/zhFN6u3lHFFbWwuD3uDXOaLJMevlHFFVVYVwbbhf54jmx2zzc4RLuKCP0Pt1jmhc7+bniB+KfkC9qx6HTh2CRWfhtQd5J/GT5Hq9XpVZSuTJxLoFJph91YfrMbLHSOSdzkPuqdwWAxmsW/CzZGPdlBdSAxk9e/ZESUlJk8dKSkoQExPT6urrjz/+OB5++GHPv92Ll2VlZUFr0ALf/pTzSAlMOpPU9m7btg3jxo1jJjOZyUxmMvMclwuGCyZDu3MXXADmAVj607e0ABYB6Ne7HzRRUYiPj5faXvKf7GuPmJgYYMJK5NyWg95ffw1kZ+P6Idfj+vte63Bbc3JyMGHChA7ndEYuM5nJTGYyUx2Zic8notxWjri4OKR2S+W1BynOPYAnY8FZmVlK5MnEugUm2H3N6pXlGci4adhNirZNpmDXrbOyZGPdlBdSAxkTJ07El19+2eSx1atXY+LEia3+jF6v92nUyaQzwRQhdyAjc2QmM5nJTGYyk5nnuFzAkCHAwYNeBzFWAJhxwQXQmOS2kwKn1LXH0KFDga+/ltLGJpkKUCKXmcxkJjOZqZ5MIp9JmFrKJPE6V2aWEnkysW6BCXZfs5Kz8Gbem14X/Gbdgp8lG+umvKCuJGo2m5Gfn4/8/HwAwNGjR5Gfn4/jx48DaPhE4+233+7Z/u6778aRI0fw+9//Hvv27cNrr72Gf//733jooYeC0fx2Nf8EJzOZyUxmMvM8zhQCGDsWOHgQAKAZOBCx99wDANBqtVjxzju4yWzG0eXLpd6+T02p5doj6MdjkHOZyUxmMpOZ6skkao+QeG1qsVg80/CpKUuJPJlYt8AEu6/NF/xWsm0yBbtunZUlG+umvKDekZGbm4tp06Z5/u2ehmH27NlYtmwZTp8+7XljAQD69euHL774Ag899BBefvllpKSk4J///CemT5/e6W33RXl5OTOZyUxmMvN8yRQC+GlOaq8sFuCnN8+Rng7Nvn1YrNEg3GjEhAkTcNNNDbcal1dUSG8nnaOWa49QOcaVymUmM5nJTGaqJ5OoM6n5E8Zq/sQy6xaYYPd1ePfh0Gv1qKqtwuGKwxiYMFCxtskU7Lp1VpZsrJvygjqQMXXq1BYjko0tW7bM68/s2LFDwVbJEx4uv7zMZCYzmclMFWa6XA13W7gHKtqTlweEhUED4G9/+5v3TFKEWq49QuUYVyqXmcxkJjOZqZ5MIp9JmFrK/YngiIgIVWUpkScT6xaYYPc1QhuBUT1GYdupbcg9ldtkIIN1C36WbKyb8oI6tVRXN3bsWGYyk5nMZGZXyhSi4c6Kn77GDhkCmM0N6160M4jhAvAAgJxRo4A2Pg2hRN9JfVR7jHdSLjOZyUxmMlM9mUTtkji1lMFgkLbYrMwsJfJkYt0Co4a+uqeX2n5qu6Jtk0kNdeuMLNlYN+VxIENBW7duZSYzmclMZnaVTCGAyZOBqKimX9HRnnUvkJ4O1NQ0DG40+nJVV2PerFn4O4DLCwuR00ZblOg7qY8qj/FOzGUmM5nJTGaqJ5OoMzkcDjgcDtVlKZEnE+sWGDX01bNOxummC36zbsHPko11Ux7vS1VQW1NXMJOZzGQmM0Ms02IBNm1q/fsZGcD27UBY088IuFwuzJs3D0vfeeenGAuKioowYcIEZdpJIUGVx3gn5jKTmcxkJjPVk0nkMwnHX1iYvM/TysxSIk8m1i0wauhr4zsyXMKFME2YIm2TSQ1164ws2Vg35XEgQ0FJSUnMZCYzmcnMrpApBHDRRef+XVICmEw4evQo+vXr1/BYZGSL2+49gxhLlwIAtFotVqxYgRtvvFGZdlLIUN0x3sm5zGQmM5nJTPVkEnUmjcRpqmRmKZEnE+sWGDX0dVjSMBjCDaipq8HBsoMY3G2wIm2TSQ1164ws2Vg35XEgQ0Hx8fHMZCYzmcnMrpBptZ5bAyMjA0hKAjQaxPXu3ep6F60NYtx0003KtZNChuqO8U7OZSYzmclMZqonk6gzyZ52RSY1T7vCugVGDX0NDwvHmJ5jsLloM3JP5XoGMli34GfJxropr2vcV6JSBw4cYCYzmclMZqo9s9kC3q1+uW3c6LnzorXMQAcx2mwndSmh8rpRKpeZzGQmM5mpnkwin0mYWkrNi9eqeTFc1i0waumrZ52MU+fWyWDdgp8lG+umPN6RQURE5y/3At5trX3RXDu3ZHZkEIOIiIiISG2ExClJbDYbAEh5Q01mlhJ5MrFugVFLX70t+M26BT9LNtZNeRzIUNDgwYOZyUxmMpOZas5sbwHv5iZNalgLo43MjRs3dmgQQ4m+k/oMHjwY+Ppr+ZkKCOnXODOZyUxmMpNIVUytTMsa7Cwl8mRi3QKjlr66BzLyTueh3lWP8LBw1k0FWbKxbsrj1FIKKi8vZyYzmclMZgYzs9G0URVFRU2nijKbgczMc9uWlDQ81tZXo2mlWmvnlClT8M9//hM6nS6gOzGUqCepj6pfN52Qy0xmMpOZzFRPJpHPJEwtZbFYYGk8batKspTIk4l1C4xa+jo4cTCiIqJgdVhRUFqgSNtkUkvdlM6SjXVTHu/IUFBpaSn69+/PTGYyk5nMDEamywWMHetZpLtfW9s2WsDbH621884778Sll16K1NRUv/LayqSupbS0FLL3slLHjmpf48xkJjOZyUyiNrmnEtFoNNBqtairq4PRaITVaoXJZILFYkFkZCRsNhsiIiLgdDohhIBOp4Pdbvds41ZXVwdrZSV0Oh2EEHC5XC22df/XaDSitrYWWq0WAOB0OqHX6+FwOBAZGYmKigrPtgaDAQ6HA2FhYdBoNHA4HDAYDLDZbC1y3dtqNBqEhYWhrq4OtbW1fvepcTvtdjt0Oh2AhmlibTabX31qrZ1CCJjNZr/61Np+0ul0sNlssFqtfvXJ235qvA/87ZO3/dTWPg3k2BNCoK6uzq8+tbef7Ha7X31qbVuXywWNRgOr1er362lsz7FYf3w9fjj2A1IiUhAeHg673Q6LxRLw66l5O4UQsNlsAb2eGu+nxvs00NdT4z55O0Y6euy1t0/9Pfbaet37euy5n89sNgf8emq8rU6ng9Vq9ezTjpzLm7/uO/J6cvdJCCHlXG61Wn3+vcY7MhQUFia/vMxkJjOZyUwfCNFkEKNNGRnA9u1+D2IADe10uVzYvHlzi+8FMojhzqSuT5Wvm07MZSYzmclMZqonk7qOJUuWYNiwYRg3blywm9Iqu93u15tWbXG/wSeL7DyZZLZN5j5QIk8mm80mdZ92JG9ccsPrctvpbQAa9qndbpfWNpnUfIyouW5KnJNk9VXNr1N/aISQcG9gCKmurkZsbCyqqqqgNWgR9WwUAMD8uBmmiK4xXxgR0XnPbAaioxv+Pz0dyMtrfaAiMjKgQQzg3MLey5cvx7vvvotbb701wAZ71/h3VkxMjNRs6jyt7sdFi4DsbGD+fOC114LWPiIiOn8lPp+Icls5Cu4pwJBuQ3jt0UXI3o+lGRlI2rkTeO894LbbOpTlfpPPaDR2uF0ys5TI+/zzz3HttddKyWLdAqOmvn5S8Alu/PeNGN1jNPLvzpfeNkBe7dRUNyWz3Fi3wMiqmz+/s/hxDgXl5uYyk5nMZCYzOztTCOCii879Oy8PiIpCbkEBYDK1/OrAIMaMGTOwdOlSuFwuzJ07FydPngy83T9Rop6kPqp73XRyLjOZyUxmMlM9mUSdyeFwwOFwqC5LiTyZWLfAqKmv43uPBwD8eOZHWOosrJsKsmRj3ZTHgQwFOZ1OZjKTmcxkZmdkNlrUG6Wl56aUyshoGKwIJLMN7jsxPv/8cwCAVqvFu+++i969e3c4W4l6kvqo4nUTxFxmMpOZzGSmejKJOpNGo4EmwA8SKZmlRJ5MrFtg1NTXlJgUJEcnwyVcyDudx7qpIEs21k15HMhQUGJiIjOZyUxmMlOJzMYDF2YzkJkJREU1fPXocW67jRs9d1zIaqd7EGPp0qUAGgYxVqxYgZtuuklKvhL1JPUJldeiUrnMZCYzmclM9WQS+UzCzORardazaKyaspTIk4l1C4za+uq+KyPnZA7rpoIs2Vg35YUHuwGdZcmSJViyZInnEyy5ubkI058bx9m2bRu6x3dHv379sGvXLgANC7W6XC6cOHECAJCRkYFDhw7BbDbDZDJh0KBB2LFjBwAgJSUFWq0Wx44dAwCMGjUKZrMZOTk5MBgMGD58OLZv3w4ASE5OhsFgwJEjRwAAI0aMQFFRESorKxEREYGMjAxs3boVANCzZ09ERUXh0KFDAIC+ffvi4MGDKC8vR3h4OMaOHYutW7dCCIGkpCTEx8fjwIEDAIDBgwejvLwcpaWlCAsLw7hx45Cbmwun04nExER0794dBQUFcDgcSEhIQHV1NUpKSgAAEyZMQF5eHhwOB+Lj45GcnIw9e/YAAAYMGACr1YrTp08DALKysrB7927Y7XbExsaib9++KC4uRllZGdLS0lBfX4+ioiIAQGZmJvbt2wer1YqoqCgMGDAAO3fu9PQNAI4fPw4AGD16NA4fPgyz2YzIyEj07t0bOTk5nnqHh4ejsLAQADBy5EgcP34cVVVVMBgMGDFihOe26169eiEyMhKHDx8GAAwfPhynTp1CRUUFAGDgwIGe3B49eiAmJgYHDx4EAAwdOhRnzpxBWVkZtFotsrKysG3bNrhcLiQlJSEhIQH79+8HAAwaNAgVFRUoLi5GeXk5xo8fj+3bt6O+vh4JCQno0aMHCgoKPM9pNptRXFwMABg/fjzy8/NRV1eHuLg4pKSkYPfu3QCA/v37w+Vyedo4duxY7NmzB3a7HTExMUhLS2tyzDqdTk+9x4wZgwMHDsBisSAqKgoDBw5E/k+fVO/WrRuKi4ubHLNHjx5FTU0NjEYjhg4diry8PABA7969ERERgaNHj3rqfeLECVRWVkKv12PUqFHYtm0bHA4HdDodTCaTp97Dhg3z1ESn0yEzM9PTl+7duyM2NtZT7yFDhuDs2bM4e/as55gtLS1FWVkZunXrhm7dumHfvn0AgPT0dFRVVeHMmTMtjtmEhAT07NkTe/fu9RyzFovFU+/BgwcjPz8ftbW1iIuLQ58+ffDjjz8CAPr164e6ujrPFEGZmZkoKCiAzWZDdHR0q+cIh8OBPn36+HWOKCwsRHV1davnCPfryJ9zxNChQ1FSUtLqOcJgMHjq7+s5wl3v1s4RkZGRMJvNfp0j3PVu7RxRVVWF2tpa7+eIwkKMmDMHpp/Oda2pGz8eO3bvBjQajBw5EhaLxXNO9vUc0fyYTUpKwh//+Ee8//77ABouBv7f//t/6NOnD3Jzc306R5SWlkKj0bR6jnCfd81ms6dNFJq8XXuYTCZkZmaisrISRUVFSAFQX1+P7T8dYx259ujXrx8KCgraPK/w2oPXHrz24LUHrz0CuPZo5RwxZMgQzzHr7Rwh49qj+TnCvc/9OUe0de1RX18PAKisrMQxyzFee5B3Ej/FW1dXBwCIjIxUVZYSeTKxboFRW18n9J6Az/Z9hq0nt2LesHlS2yaT2uqmVJZsrFsnEOeZqqoqAUBUVVUJc61ZIBsC2RDmWrP059qyZQszmclMZjJTVqbLJURNjRDp6UI0fB6s6VdGRsP3zeaGL5dLajudTqeYO3euACAACK1WK5555pkOZXrTuJ2Nf2dR6PK2H7ds2SJEdnbDsTt/vpTnUeK1qFQuM5nJTGYyUx2ZCc8lCGRDFJQWCCF47dFVyN6PZzIyGq5Z3n23w1l2u13Y7XYJrZKbpUTeqlWrpGWxboFRW1/XHFkjkA2R+v9SpbdNCHm1U1vdlMpyY90CI6tu/vzOOm/uyCAiohDlnkbqoovOrX0BAOnpDQt5uz8hFhkp9dNizd1///0tppPq06ePYs9HRERERKQqEqaWslqtAAC9Xq+qLCXyZGLdAqO2vmYlZ0EDDY5VHUPh2UJ0j+zOugUxSzbWTXkcyFBQeno6M5nJTGYysyOZLhcwdmzTAQygYRHv7duBMN+XeupoO2+++WYsXboUtbW1njUxysvLO5TpjRL1JPVJT08Hvv5afqYCQu68wUxmMpOZzCSSSkj8sJDJZFJllhJ5MrFugVFbX2P0MRiaNBR7S/diT+Ue9EvqJ6llcqmtbkplyca6KY+LfSuourqamcxkJjOZ6YvGi3dbLKgpLm5YxHvIkKaDGBkZQE1Nw50YfgxiyGjnlClT8OWXX+LDDz/0LOyt2nqS6oXSsRMqbWUmM5nJTGYSqZ/FYoHFYlFdlhJ5MrFugVFjX90Lfm86tol1C3KWbKyb8jiQoSD3wnTMZCYzmcnMNrhcQGYmEBXl+UodPhyIjgZ+WtgS6ennBjCiogKaQsrfdrpcLohmt89PmTIFN954Y8CZvlAik9QnlI6dUGkrM5nJTGYyk0hhEqaWioyMlLbYrMwsJfJkYt0Co8a+jk9uGMjIL81n3YKcJRvrpjwOZBARUfAI4X3qqMYyMoB9+wIewAiEy+XCvHnz8NRTT7UYzCAiIiIiosDYbDbYbDbVZSmRJxPrFhg19nVCygQAQO7pXFis6vyEvBrrpkSWbKyb8rhGhoImTJjATGYyk5nM9EYIwGptmErKPYjRfPFuN0mLePvaTvcghnth77CwMCxatKhDmf5QIpPUZ8KECdLXyFDq2AmV45yZzGQmM5lJpH4RERGqzFIiTybWLTBq7OvI7iNhCDegqrYKxy3HkRCfIKFlcqmxbkpkyca6KY93ZCgoLy+PmcxkJjOZ2ZwQwOTJDXdY9OjROKjhMZMJefv3AyZTw5ekuzB8aWfzQQytVouRI0d2KNNfSmSS+oTSsRMqbWUmM5nJTGYSKUzCncpOpxNOp1NCY+RmKZEnE+sWGDX2VafVIbNXJgBg68mtMpolnRrrpkSWbKyb8jiQoSCHw8FMZjKTmcxszmoFNm1q+tikSQ2DFoFm+qC9TG+DGCtWrPAs7B1IZiCUyCT1CaVjJ1TaykxmMpOZzCRSiMTpXYUQ0qZulZmlRJ5MrFtg1NpX9zoZ24u3dzhLCWqtm+ws2Vg35XFqKQXFx8czk5nMZCYzm2v8y7OkpGEAo9n0UZ3dzkAGMdrLDJQSmaQ+oXTshEpbmclMZjKTmUQKk/AmmE6nk9AQ+VlK5MnEugVGrX0d31vdAxlqrZvsLNlYN+XxjgwFJScnM5OZzGQmM4GGP3osFsBsBjIzzz3eyvRRndnOQAcx2srsCCUySX1C6dgJlbYyk5nMZCYziZQhJN6RYbfbYbfbVZelRJ5MrFtg1NpX94Lfu87sQm19bYfzZFNr3WRnyca6KY8DGQras2cPM5nJTGae35lCnBu8iIoCoqOBgwcbvpeR0XAnRhDb2ZFBjNYyO0qJTFKfUDp2QqWtzGQmM5nJTCL1M5lMMDWaUlYtWUrkycS6BUatfe0X1w+JxkQ4XA7kF+d3vGGSqbVusrNkY92Ux4EMIiLqOPcdF42/3AMY0dFAfn7T7TMygO3bpc63G4iSkhKsXr0agP+DGERERERE5xUJU0tZLBZYLBYJjZGbpUSeTKxbYNTaV41GgzHdxwBQ54Lfaq2b7CzZWDflcY0MBQ0YMICZzGQmM7t+Zv/+wOTJLRfwbi4jA9i4sWHwotmaGC0yO6nvvXr1wrp163DZZZfh+eef93sQI1T2EalPKB07odJWZjKTmcxkJpFCJH74SPanlWVS86eVWbfAqLmvE/tMxLfHvsXWU+obyFBz3Xi8BT8rmDiQoSCr1cpMZjKTmV0+01ZW1vYghnsAw8taGK3pzL4PGDAABQUF0Ov10jI7QolMUp9QOnZCpa3MZCYzmclMIvVzfyI4IiJCVVlK5MnEugVGzX0dkTACAJBTlNPhLNnUXDceb8HPCiZOLaWg06dPM5OZzGRml88sbpxZUtIwpVTjr7y8hvUx/Pgkl1J9d7lceOONN+BwOJp8L5BBDHembEpkkvqE0rETKm1lJjOZyUxmEilMwtRSRqMRRqNRQmPkZimRJxPrFhg193VS2iQAwMHygzhrPSslUxY1143HW/CzgokDGUREFDghMOzuu8/922Rq+RXkdTDc3At7z58/H7fcckuLwQwiIiIiIlKW3W6H3W5XXZYSeTKxboFRc19NGhMGxg0EAGwp2iIlUxY1143HW/CzgokDGQrKyspiJjOZycyunWm1wnTgQMP/Z2Q0rH0hgex2ulwuvPnmm1i6dCkAYOXKlcjJ6fgtvCGxj0iVQunYCZW2MpOZzGQmM0mNNmzYgGuvvRbJycnQaDT47LPP2v2Z9957D6NHj0ZkZCR69eqFO+64A2VlZco3thPodDrodDrVZSmRJxPrFhg191Wn02FC7wkA1DeQofa68XgLblYwcSBDQbt372YmM5nJzK6bKQTw0zyLAM4t5C2BzHa678RYtmwZAECr1WLFihWYPHlyh7NVv49ItULp2AmVtjKTmcxkJjNJjSwWC0aPHo0lS5b4tP0PP/yA22+/HXfeeSf27NmDjz76CFu3bsVdd92lcEt9IGFqKSEEhIQc2VlK5MnEugVGzX0VQmB8r/EAgM1Fm6VkyqL2uvF4C25WMHGxbwUpccsOM5nJTGYGPdM9gHHRRUB+/rnHJU4hJavv7kEM950Y7kGMm266SUq+avcRqV4oHTuh0lZmMpOZzGQmqdGVV16JK6+80uftN2/ejLS0NNx///0AgH79+uE3v/kNnnvuOaWa2C4h8Trf5XKpMkuJPJlYt8Coua8ulwtZPRvustt6ciucLie0YVpp+R2h9rqpFeumvPNmIGPJkiVYsmQJnE4nACA3Nxdh+nM3pGzbtg3d47ujX79+2LVrFwAgNTUVLpcLJ06cAABkZGTg0KFDMJvNMJlMGDRoEHbs2AEASElJgVarxbFjxwAAo0aNgsPhQE5ODgwGA4YPH47t27cDAJKTk2EwGHDkyBEAwIgRI1BUVITKykpEREQgIyMDW7duBQD07NkTUVFROHToEADAYDDg4MGDKC8vR3h4OMaOHYutW7dCCIGkpCTEx8fjwE/TvAwePBjl5eUoLS1FWFgYxo0bh9zcXDidTiQmJqJ79+4oKChATU0NysvLUV1djZKSEgDAhAkTkJeXB4fDgfj4eCQnJ2PPnj0AgAEDBsBqtXoWmsvKysLu3btht9sRGxuLvn37oqamBjk5OUhLS0N9fT2KiooAAJmZmdi3bx+sViuioqIwYMAA7Ny5EwDQt29fAMDx48cBAKNHj8bhw4dhNpsRGRmJqKgoz1QwKSkpCA8PR2FhIQBg5MiROH78OKqqqmAwGDBixAjk5uYCAHr16oXIyEgcPnwYADB8+HCcOnUKFRUVsFqtAODJ7dGjB2JiYnDw4EEAwNChQ3HmzBmUlZVBq9UiKysL27Ztg8vlQlJSEhISErB//34AwKBBg1BRUYGamhps3boV48ePx/bt21FfX4+EhAT06NEDBQUFAICBAwfCbDajuLgYADB+/Hjk5+ejrq4OcXFxSElJ8Xzaqn///k3aOHbsWOzZswd2ux0xMTFIS0trcsw6nU5PvceMGYMDBw7AYrEgKioKAwcORP5PbzyHhYWhuLi4yTF79OhR1NTUwGg0YujQocjLywMA9O7dGxERETh69Kin3idOnEBlZSX0ej1GjRqFbdu2oaamBseOHYPJZPLUe9iwYSguLkZ5eTl0Oh0yMzM9fenevTtiY2M99R4yZAjOnj2Ls2fPeo5Zi8WCnJwcdOvWDd26dcO+ffsAAOnp6aiqqsKZM2daHLMJCQno2bMn9u7d6zlmLRaLp94xMTHIz89HbW0t4uLi0KdPH/z4448AGv5QqKurw8mTJz3HbEFBAWw2G6Kjo1s9R9TU1KC2ttavc0RhYSGqq6tbPUe4X0f+nCOGDh2KkpKSVs8RERERnvr7eo5w17u6uholp09jxJw556aT+onzgguQ++OPgEbj0znCXe/WzhE1NTXYs2ePX+eIIUOGeI7ZlJQUhIWF4de//jX++9//AmgYxHj66aeRnp4Op9Pp0zmi+THb/BxhMBhw6NAhv84RpaWl0Gg0rZ4jampqUFZWBrPZ7GkThSZv1x4mkwmZmZmw2+0oKipCCoD6+nps/+kY68i1R2RkJAoKCto8r/Dag9cevPbgtUfIXXt4OUfU19fDbDb7dY7ojGuP5ueIxn8P+nqO6Oxrj/r6egBAZWUljlmO8dpDBSZOnIgnnngCX375Ja688kqcOXMG//nPf3DVVVe1+jO1tbWora31/Lu6urozmhoQ2dOuyKTmaVdYt8Coua86nQ6jeo5CdEQ0aupqsPvMbozuOVpafkeovW5qxbopTyO6wn0lfqiurkZsbCyqqqqgNWgR9WwUAMD8uBmmCJPU57JarYiUNF88M5nJTGZ2eqYQwE9vuHn+nZkJ/PSHNAAgIwPW//0PkUlJUu/I6Gjfvd2JsXz5cvzyl7+U1UQAyu+jxr+zYmJipD4PdR5v+9FqtSLyb38DsrOB+fOB117r8PMocTwqlctMZjKTmcxUR2bi84kot5Wj4J4CDOk2hNceCtNoNPj0008xY8aMNrf76KOPcMcdd8But6O+vh7XXnstPv7441bfiMrOzsaiRYtaPL5ixQopx8u4P/0JPXNzkX/vvThx+eUdynK/BaWR8LeDzCwl8lwuF8LC5MzozroFRs19dWc9degp7KzZifl95uPKJN/v3vJGVu1CoW6y2gawboGSVTer1YpbbrnFt2sPcZ6pqqoSAERVVZUw15oFsiGQDWGuNUt/ri1btjCTmcxkZmhmOp1CZGQI0TB80fIrPV2ImhohXC5V9v3ZZ58VAAQAodVqxUcffaTKdraX2fh3FoUub/txy5YtQmRnN7ye5s+X8jxKHI9K5TKTmcxkJjPVkZnwXIJANkRBaYEQgtceSgMgPv300za32bNnj+jVq5d4/vnnxc6dO8XXX38tRo4cKe64445Wf8Zut4uqqirP14kTJ6Tux9Pjxzdcs/zznx3Oqq2tFbW1tRJaJTdLibxVq1ZJy2LdAqPmvrqzFqxZIJANcfunt3c4U1btQqFuMrFugZFVN3+uPc6bqaWIiMhHLhcwZEjTOy8ay8gAtm8HJH1KRgnz58/Hp59+iu3bt3vWxHBP0UBEREREpFbPPvssJk2ahEcffRRAw7RwJpMJF110Ef785z+jV69eLX5Gr9dDr9d3dlMDYrFYAAARERGqylIiTybWLTBq7qs7a2KfiQCAzSfUs+B3KNSNx1vwsoKJAxkKSktLYyYzmclMdWe2N31UejqQl9d02qjIyCb/VmPfY2Nj8c033yAnJweX/3T7uxrb2VmZpD6hdOyESluZyUxmMpOZ1BVYrVaEhzd9q0arbVgAWAR7ZnAJz28yyZvSW2aWEnkysW6BUXNf3VkXGC4AABwsP4gyaxkSIxOlPUegQqFuasS6KY8DGQpyL5zGTGYyk5mqzBQCmDwZ2LTJ+8bp6cC+fe3eeaGGvrtcLpjN5ibzKcbGxnoGMQLJ9EWoZJL6hNKxEyptZSYzmclMZpIamc1mHDp0yPPvo0ePIj8/HwkJCejbty8ef/xxnDx5Em+//TYA4Nprr8Vdd92F119/HdOnT8fp06fx4IMPYvz48UhOTg5WN6RR8yeM1fyJZdYtMGruqzsrIT4BgxMHY3/Zfmwp2oKrB13d4eyOCoW68XgLXlYwqXdekC6gqKiImcxkJjPVm2m1tj6IkZHh0yBGi0xJ/Ml0L+w9depUlJeXS8n0VahkkvqE0rETKm1lJjOZyUxmkhrl5uZizJgxGDNmDADg4YcfxpgxY/DUU08BAE6fPo3jx497tp8zZw4WL16MV199FSNGjMDNN9+MwYMH45NPPglK+2UzGo0wGo2qy1IiTybWLTBq7mvjLM/0UkXqmF4qVOqmNqyb8nhHBhHR+arxreElJUDjWw2bTR+lVu5BjKVLlwIArrzySmzatMlz+z0RERERUTBNnTq1zSmhli1b1uKx++67D/fdd5+CrQqQhKmlamtrAQAGg0FVWUrkycS6BUbNfW2cdUHvC7Asf5lqBjJCpW5qw7opjwMZCsrMzGQmM5nJTHVmCgFcdNG5b5hMTQcyAsmUyJfM5oMYWq0Wjz76aKuDGCG3j6hLy8zMBL7+Wn6mAkLlOGcmM5nJTGYSKUTiB5xkfuBI9oeX1PxhKNYtMGrua+Ms9x0ZW09uhdPlhDYsuDUNlbqpDeumPE4tpaB9+/Yxk5nMZKb6MoUASkuB/PyGBzMyGu7A6EimZO1lehvEWLFiBW666aaAMwMRKpmkPqF07IRKW5nJTGYyk5lERBSKhicNR3RENMx1Zuw+szvYzSFSLQ5kKMhqtTKTmcxkpjoyhQAsFtjPngUyM4EePc59b+PGDn3KqrP7HsggRnuZgQqVTFKfUDp2QqWtzGQmM5nJTCKFSZhayul0wul0SmiM3Cwl8mRi3QKj5r42ztKGaTG+93gA6lgnI1Tqpjasm/I4tZSCoqKimMlMZjIz+JkuFzB2LJCfj3HNvzdpUsBTSrl1Zt8DHcRoK7MjQiWT1CeUjp1QaSszmclMZjKTSBlC4tRSer1elVlK5MnEugVGzX1tnjUxZSLWHF2DzUWbcXfW3dKeJxChVDc1Yd2Ux4EMBQ0YMICZzGQmM4ObKYRnEKOJjIyGOzFMpg7PedtZfe/IIEZrmR0VKpmkPqF07IRKW5nJTGYyk5lE6mez2QDIWXBWZpYSeTKxboFRc1+bZ7nXydhStKXD2R0VSnVTE9ZNeZxaSkE7d+5kJjOZyczgZlqt5wYx0tOx7bvvALMZyMsDoqKkLNzXWX13uVyw2+0A/B/EaC2zo0Ilk9QnlI6dUGkrM5nJTGYyk0hhEqaWMplMMHXwjnAlspTIk4l1C4ya+9o864KUCwAAB8oOoMxaJuU5AhVKdVMT1k15vCODiOh8kZcH1549HZ5KKljCw8Px9ttvIzw8HNddd51fgxhERERERBR8FosFABAREaGqLCXyZGLdAqPmvjbPSjAmYHDiYOwv248tRVtw9aCrO/wcstqmpjweb8HPCiYOZCiob9++zGQmM5kZ3MzGn5rSaNTbTh8z3YMZMjM7IlQySX1C6dgJlbYyk5nMZCYzidRP9qeVZVLzp5VZt8Coua/esib2mYj9ZfuxuWhzUAcyQq1uasG6KY9TSxERdVUuF5CZGexWBMzlcuHRRx/F/v37g90UIiIiIiKSMLWUxWLxfDJYTVlK5MnEugVGzX31ljUxpWGdjM1Fm6U8R6BCrW5qwbopjwMZCjp+/DgzmclMZgYn0+UChgwBDh5s+HdGBhAZqb52tqKwsBDz5s3DCy+8gKlTp0oZzAiVviuRSeoTSsdOqLSVmcxkJjOZSaQQCevquRkMBmmLzcrMUiJPJtYtMGruq7esC/tcCADIKcpBvateyvMEItTqphasm/I4kEFE1NUIAYwde24QIz0d2L5d6h8gSnK5XHjmmWewdOlSAEBpaSkKCgqC3CoiIiIiovOchDsyHA4HHA6HhMbIzVIiTybWLTBq7qu3rGFJwxBniIPFYcHO4p1SnicQoVY3tWDdlMeBDAWNHj2amcxkJjM7P9NqBfLzG/4/PR3Ytw8IC+tYZhtkZrpcLsybNw///e9/AQBarRYrVqzAjBkzOpyt9r4rmUnqE0rHTqi0lZnMZCYzmUmkDCHxA1FhYWEIC5PzVpTMLCXyZGLdAqPmvnrLCtOEee7K+P7491KeJxChVje1YN2UF/o9ULHDhw8zk5nMZGbnZQoBWCwNX255eZ5BjIAyfSAr0z2I4b4Twz2IcdNNN0nJV3Pflc4k9QmlYydU2spMZjKTmcwkUj+NRgONpIERmVlK5MnEugVGzX1tLWtSn0kAgB9O/CDleQIRinVTA9ZNeeHBbkBnWbJkCZYsWQKn0wkAyM3NRZj+3Jt727ZtQ/f47ujXrx927doFAEhNTYXL5cKJEycAABkZGTh06BDMZjNMJhMGDRqEHTt2AABSUlKg1Wpx7NgxAMCoUaNw+vRpmM1mGAwGDB8+HNu3bwcAJCcnw2Aw4MiRIwCAESNGoKioCJWVlYiIiEBGRga2bt0KAOjZsyeioqJw6NAhAEB9fT0OHjyI8vJyhIeHY+zYsdi6dSuEEEhKSkJ8fDwOHDgAABg8eDDKy8tRWlqKsLAwjBs3Drm5uXA6nUhMTET37t1RUFCAiooK9OrVC9XV1SgpKQEATJgwAXl5eXA4HIiPj0dycjL27NkDABgwYACsVitOnz4NAMjKysLu3btht9sRGxuLvn374sSJEzCbzUhLS0N9fT2KiooAAJmZmdi3bx+sViuioqIwYMAA7NzZcLtc3759AZyb93X06NE4fPgwzGYzIiMjYTabkZOT46l3eHg4CgsLAQAjR47E8ePHUVVVBYPBgBEjRiA3NxcA0KtXL0RGRnou+ocPH45Tp06hoqICVVVVGD58uCe3R48eiImJwcGfpuQZOnQozpw5g7KyMmi1WmRlZWHbtm1wuVxISkpCQkKCZ+7+QYMGoaKiAidOnIDFYsH48eOxfft21NfXIyEhAT169PBMjzNw4ECYzWYUFxcDAMaPH4/8/HzU1dUhLi4OKSkp2L17NwCgf//+KC0t9bRx7Nix2LNnD+x2O2JiYpCWltbkmHU6nZ56jxkzBgcOHIDFYkFUVBQGDhyI/J8+qW+321FcXNzkmD169ChqampgNBoxdOhQ5OXlAQB69+6NiIgIHD161FPvEydOoLKyEnq9HqNGjcK2bdtQUVGBqKgomEwmT72HDRuG4uJilJeXQ6fTITMz09OX7t27IzY21lPvIUOG4OzZszh79qznmC0qKoLZbEa3bt3QrVs37Nu3DwCQnp6OqqoqnDlzpsUxm5CQgJ49e2Lv3r2eY9ZisXjqLYRAfn4+amtrERcXhz59+uDHH38EAPTr1w91dXU4efKk55gtKCiAzWZDdHR0q+eIiooKDBw40K9zRGFhIaqrq1s9R7hfRz6dIw4exLBf/xrRP/XDQ6Npco6oqKjw1N/Xc4S73q2dI8xmM1JTU/06R7jr7T5HHD9+HM8884znToywsDD87W9/wzXXXONpb3vniCFDhniOWW/niMbnZF/PEc2P2ebnCIfDgUOHDvl1jigtLYVGo2n1HFFRUYGePXvCbDbzzYoQ5+3aw2QyITMzE6dOnUJsURFS0PC7fftPx1hHrj2cTicKCgraPK/w2oPXHrz24LWHtGuPn84RQ4cORUlJSavnCLVeezQ/R7jr7885oitce9TXN8zBXllZiWOWY7z2oLZJmlpKFtnTpKh52hXWLTBq7mtrWZP7TgbQcEeGECIobz6HYt3UgHXrBOI8U1VVJQCIqqoqYa41C2RDIBvCXGuW/ly7du1iJjOZyczOyaypEaLhT4tzX5MmCeFyBZ7po45mOp1OMXfuXAFAABBarVa88MILklp3jhr73l5m499ZFLq87cddu3YJkZ3d8FqdP1/K8yhxPCqVy0xmMpOZzFRHZsJzCQLZEAWlBUIIXnt0FbL348kLL2y4ZlmypMNZNptN2Gw2Ca2Sm6VE3qpVq6RlsW6BUXNfW8uy1lmF7k86gWyII+VH/MqUVbtQrFtHsG6BkVU3f35nnTd3ZATDkCFDmMlMZjJT+UyXC8jMPPfvkhLAZAIiI1ss8K3Gvn/55ZctppO6/vrrZTStCTX2vbMySX1C6dgJlbYyk5nMZCYzidTPZrMBAAwGg6qylMiTiXULjJr72lqWUWfE2OSx2FK0Bd8f/x794vt1+LlktU0NeTzegp8VTFwjQ0Hu24yZyUxmMlOxTCGAsWOBn6YbQEYGkJTUMJDh5RZUNfb9mmuuwdNPP91kTQw1tjOUM0l9QunYCZW2MpOZzGQmM4kUJmFqKZPJBJPJJKExcrOUyJOJdQuMmvvaVlaw18kI1boFG+umPA5kEBGFMosF+GnucaSnA9u3ex3AULsFCxZg9+7d0hb2JiIiIiIiSST+fWGxWGCxWFSXpUSeTKxbYNTc17ayGq+TEQyhWrdgY92Ux6mlFJSSksJMZjKTmcplCgFcdNG5f+flAWFtj0+roe8ulwt79uzByJEjmzzeeKoENbSzK2WS+oTSsRMqbWUmM5nJTGYSqZ/sTyvLpOZPK7NugVFzX9vKurDPhQCAPaV7UGGrQLwxXtrz+iJU6xZsrJvyOJChoPBw+eVlJjOZyUwPq/Xc3RgZGQ3TSXU0MwD+ZLpcLsybNw8ffPABVq1ahcsuu6zDmb46nzNJfULp2AmVtjKTmcxkJjOJmnLPia7RaKDValFXVwej0Qir1QqTyQSLxYLIyEjYbDZERETA6XRCCAGdTge73e7Zxj2hlKOuDpbKSuh0Oggh4HK5Wmzr/q/RaERtbS20Wi0AwOl0Qq/X48yZMzAYDNDpdJ5tDQYDHA4HwsLCoNFo4HA4YDAYYLPZWuS6t9VoNDCbzXA4HOjRo4fffWrcTrvdDp1Oh8rKSgghkJiY6FefWmunEAJms9mvPrW2nxwOB+x2O7p16+ZXn7ztp+LiYs8+8LdP3vZTW/s0kGNPCIG6ujq/+tTafqqurobT6URSUpJffWpt27KyMmg0GsTHxwf8enL/t66uDnV1dUhISGjRpzhTHAbGDcShykP4puAbXD/sep/2kxACNpstoNdT4/1UUlLi2aeBvp4a96m0tLTFMRLosefrPvX32LPZbAG9nhpvW1tbC4fDgfj4+IBfT423db/uk5KSAn49tfa6D+T11LxPQghUVFR0+FxutVp9/r3GqaUUVFhYyExmMpOZymU2nqN240afbvkOZt/dgxhLly6F3W7HzJkzUVZW1qFMf5zPmaQ+oXTshEpbmclMZjKTmXS+W7JkCYYNG4Zx48YFuymtioiIkLbYrF6vh16vl5LlzouIiJCWJ5PMvsrcB0rkyaTEMSIrr73jbXzyeABAzukcKc/nDzUfI2p+nRoMBqnHm8FgkNZXNb9O/cGPcxARhaLm00qpfF2MxoMYAKDVarF06VIkJiYGuWVERERERF3DPffcg3vuuQfV1dWIjY2F0WhETEyM5/uRkZEA4Hmjzf0Gmbc33oxGo2cb609/a+h0OsTFxbW5beP/envTzN0G9yeW3du6Mxpz/3zzXPe21dXVCA8Pb/Lmsq998tZOp9Pp2c6fPrXWTo1Gg6ioKL/6BHjfT9XV1TAajZ7v+donb9s23wf+9MnbfvJln/pz7Gk0GkRERPjVp9a2dX/S3GAw+NWn1rZ1OBye/gT6enL/171Pm0/54972koGX4P297yP3TG6T9rfVTo1G0+T49aVP3vZT830ayOupMXfdmh8jgRx7/u5TX/ZT87oFeuxVV1fDYDAE9Lr3tm11dTUiIyNb7NNAjj1fXvf+nvfcdyf50ydv24rGH9JtB+/IUFDz+d+ZyUxmMlNaZvNppZpd0AaUGaD2Mr0NYqxYsaLNhb27xD5SUSapTygdO6HSVmYyk5nMZCaRwvx4s6k1Go0GGkkfwpKZpUSeTKxbYNTc1/ayJvWZBADYdmobautrpTynr0K5bsHEuimPAxkKOn78ODOZyUxmdixTCMBi8f7l5uO0Uoq2sxWBDGK0lxmo8zmT1CeUjp1QaSszmclMZjKTSCES3/zSarWeudbVlKVEnkysW2DU3Nf2sgYlDkK3yG6w19uRdzpPynP6KpTrFkysm/I4kKGgqqoqZjKTmcwMPLOyEpg8GYiKavnVo8e5Df34w6Iz+x7oIEZbmR1xPmeS+oTSsRMqbWUmM5nJTGYSqZ97gWO1ZSmRJxPrFhg197W9LI1G47kr44cTP0h5Tl+Fct2CiXVTHgcyFKTEIirMZCYzz5/MSADYtKntjSZN8nlaKaBz+z5//vyABjHayuyI8zmT1CeUjp1QaSszmclMZjKTSGESppZqbf7+YGcpkScT6xYYNffVl6zJfScDAL4//r2U5/RVqNctWFg35XEgQ0EjRoxgJjOZycz2tTJ91LDU1HPblJQAZnPLLz+mlepwO/3MvPzyyxEeHu73IEZbmR1xPmeS+oTSsRMqbWUmM5nJTGYSqZ/VaoXValVdlhJ5MrFugVFzX33JanxHhj8LIndUqNctWFg35XEgQ0G5ubnMZCYzmdk2IVqdPkqbnHxuO5PJ+5ef89V2Zt9vvPFGrFixwu9BjLYyO+J8ziT1CaVjJ1TaykxmMpOZzCRSP5PJBJPJpLosJfJkYt0Co+a++pKV2SsThnADzlrP4kDZASnP64tQr1uwsG7KCw92A4iIzmtWq/Tpo4JFCAFNs4GVG2+8MUitISIiIiIiqSR8ItxisQAAIiIiVJWlRJ5MrFtg1NxXX7L04XqMSx6Hjcc34ocTP2Bwt8Edfl5ZbQtWHo+34GcFU9DvyFiyZAnS0tJgMBgwYcIEbN26tc3tX3rpJQwePBhGoxF9+vTBQw89BLvd3kmt9U+vXr2YyUxmMtN3zaaPOlFQEND0UW1Rqu/uhb2XLFkiLVO28zmTmlLDtUcoHTuh0lZmMpOZzGQmkTKEpL9FACAyMhKRkj6kJTNLiTyZWLfAqLmvvmYFY52MrlC3YGDdlBfUOzI+/PBDPPzww3jjjTcwYcIEvPTSS5g+fTr279+P7t27t9j+/fffx2OPPYa33noLF154IQ4cOIA5c+ZAo9Fg8eLFQehB25Q4QJjJTGZ2sczGn2pyTxf1E2O3bk3+LYMSfTcYDJg3bx6WLl2Kt956CxqNBr/97W87lKmqfdQFMukctVx7hNKxEyptZSYzmclMZhKpn81mAwDo9XpVZSmRJxPrFhg199XXLPdAxsbjGzv8nL7qCnULBtZNeUG9I2Px4sW46667MHfuXAwbNgxvvPEGIiMj8dZbb3ndftOmTZg0aRJuu+02pKWl4fLLL8ett97a7icpg+Xw4cPMZCYzmdk6IYCLLpKb2Q7ZmS6XC3feeSeWLl0KANBqtV7fDPZXKPQ9lDLpHLVce4TSsRMqbWUmM5nJTGYSKUzC1FIRERHSpjaRmaVEnkysW2DU3Fdfsyb1mYQwTRgOlR/CqZpTUp67PV2hbsHAuikvaAMZdXV12L59Oy699NJzjQkLw6WXXorNmzd7/ZkLL7wQ27dv97x5cOTIEXz55Ze46qqrOqXNRERSWSxAfn7D/2dkhMQ6GI25p5P673//C6BhECOQhb2JOguvPYiIiIgCIHFqKafTCafTqbosJfJkYt0Co+a++poVa4hFRs8MAMCGYxukPHd7ukLdgoF1U17QppY6e/YsnE4nevTo0eTxHj16YN++fV5/5rbbbsPZs2cxefJkCCFQX1+Pu+++G0888USrz1NbW4va2lrPv6urq+V0wAfDhw9nJjOZyUzvmt+N4WUdDFW0sxXuQYzGd2LIHMRQc99DMZMaqOnaY/jw4cDXXwfYE++UOnZC5ThnJjOZyUxmEqmfkHBXhxJZSuTJxLoFRs199Sfr4r4XI+90HjYc24BbRtwirQ2t6Sp162ysm/KCukaGv9atW4dnnnkGr732GiZMmIBDhw7hgQcewNNPP40//vGPXn/m2WefxaJFi1o8npubizD9uRtStm3bhu7x3dGvXz/s2rULAJCamgqXy4UTJ04AADIyMnDo0CGYzWaYTCYMGjQIO3bsAACkpKRAq9Xi2LFjAIBRo0YhPz8fOp0OBoMBw4cPx/bt2wEAycnJMBgMOHLkCABgxIgRKCoqQmVlJSIiIpCRkeH55GfPnj0RFRWFQ4cOAWiYE9VgMKC8vBzh4eEYO3Ystm7dCiEEkpKSEB8fjwMHDgAABg8ejPLycpSWliIsLAzjxo1Dbm4unE4nEhMT0b17dxQUFMBsNmPMmDGorq5GSUkJAGDChAnIy8uDw+FAfHw8kpOTsWfPHgDAgAEDYLVacfr0aQBAVlYWdu/eDbvdjtjYWPTt2xc5OTmIiopCWloa6uvrUVRUBADIzMzEvn37YLVaERUVhQEDBmDnzp0AgL59+wIAjh8/DgAYPXo0Dh8+DLPZjMjISISHh3veDEpJSUF4eDgKCwsBACNHjsTx48dRVVUFg8GAESNGIDc3F0DDgniRkZGe27CHDx+OU6dOoaKiAjabDVOnTkVOTg6AhjezYmJicPDgQQDA0KFDcebMGZSVlUGr1SIrKwvbtm2Dy+VCUlISEhISsH//fgDAoEGDUFFRgaNHjyI6Ohrjx4/H9u3bUV9fj4SEBPTo0QMFBQUAgIEDB8JsNqO4uBgAMH78eOTn56Ourg5xcXFISUnB7t27AQD9+/dHYWEhXC4XAGDs2LHYs2cP7HY7YmJikJaW1uSYdTqdnnqPGTMGBw4cgMViQVRUFAYOHIj8n+4A0Gq1SElJaXLMHj16FDU1NTAajRg6dCjy8vIAAL1790ZERASOHj3qqfeJEydQWVkJvV6PUaNGYdu2bTCbzRg4cCBMJpOn3sOGDUNxcTHKy8uh0+mQmZnpqXf37t0RGxvrqfeQIUNw9uxZnD171nPMbt26FSaTCd26dUO3bt08bzamp6ejqqoKZ86caXHMJiQkoGfPnti7d6/nmLVYLJ56x8XFwWazoba2FnFxcejTpw9+/PFHAEC/fv1QV1eHkydPeo7ZgoIC2Gw2REdHt3qOMJvNmDx5su/niAEDYPxpX9gGD4ZOr8f2n+riPkfs2rULUVFRfp0jhg4dipKSklbPETU1NZ5Fin09R7jr7T5HuFwu/N///V+TQYxly5ahT58+yMnJ8ekc4a53a+eIM2fOoGfPnn6dI4YMGeI5Zr2dI3bu3Inw8HC/zhHNj9nm5wij0YjIyEi/zhGlpaXQaDStniPMZjMyMjJgNps5fYQKyL72MJlMyMzMRF5eHvoXFSEFQH19vef135Frj6ioKISFhaG6uprXHrz24LUHrz28/n1SWFjY5jlCrdcezevtdDoxatQov84RvPbwfu1RX18PAKisrMQxyzFee1DbJLwRptPpJDREfpYSeTKxboFRc1/9ybo49WK8lPNSp92R0VXq1tlYt04ggqS2tlZotVrx6aefNnn89ttvF9ddd53Xn5k8ebJ45JFHmjz2zjvvCKPRKJxOp9efsdvtoqqqyvN14sQJAUBUVVUJc61ZIBsC2RDmWrOUfjW2ZcsWZjKTmcz0rqZGiIY/BRr+X0amDzqa6XQ6xdy5cwUAAUBotVrxzDPPSGrdOWrsezAyq6qqPL+zqOPUcO3htmXLFiGysxvOAfPnd6xjjTMVEIqvHWYyk5nMZKZvEp5LEMiGKCgtEELw2qOrkL0fT0yZ0nDNsnhxh7PKy8tFeXl5xxslOUuJvFWrVknLYt0Co+a++pN1xnzG8/5lqaW01e1k1a6r1M1XrFtgZNXNn99ZQVsjIyIiAmPHjsWaNWs8j7lcLqxZswYTJ070+jNWqxVhYU2brNVqAbR+i4xer0dMTEyTr86ixGgXM5nJzBDNFKJhTQyLBTCbgczMc99rZc5ZNfa9sLAQn332GYBz00lNnz5dQsuaUmPfQzmTGqjp2iOUjp1QaSszmclMZjKTSP1MJhNMJpPqspTIk4l1C4ya++pPVpIpCcOShgEAvj/+vZTnb0tXqVtnY92UF9DUUsePH8exY8dgtVqRlJSE4cOHQ6/X+53z8MMPY/bs2cjKysL48ePx0ksvwWKxYO7cuQCA22+/Hb1798azzz4LALj22muxePFijBkzxjO9wx//+Edce+21njcV1CSz8RuVzGQmM8/fTCGAyZOBTZtafq+NRb7V2Pf+/fvj22+/xZVXXoklS5YotrC3Gvseypl0jlquPTIzM4HPP5fSpyaZCgiV45yZzGQmM5lJpDAJU0tZLBYADR8wUVOWEnkysW6BUXNf/c2akjoFe0v3YsOxDZgxZEaHn78tXalunYl1U57Pd2QUFhbiD3/4A1JTU9GvXz9MmTIFV155JbKyshAbG4vLLrsMH330kWcuXV/84he/wAsvvICnnnoKGRkZyM/Px9dff+1ZhPP48eOeeU4BYMGCBfjd736HBQsWYNiwYbjzzjsxffp0/OMf//Cjy53HPa8pM5nJzPM4UwigtLT1QYzt21u9I0Otfc/MzMThw4c9gxhqbSczyRu1XHuE0rETKm1lJjOZyUxmEimklb9XAqHmTxir+RPLrFtg1NxXf7MuTr0YALD+2Hopz9+WrlS3zsS6Kc+nOzLuv/9+LF++HNOnT8ef//xnjB8/HsnJyTAajSgvL8fu3buxceNGPPXUU1i0aBGWLl2KcePG+dSAe++9F/fee6/X761bt65pY8PDsXDhQixcuNCnbCKioBACsFob/nvRRcBPi5wCAEpKAPcvj8hIqX8UKMHlcuGDDz7Arbfe2mR6naioqCC2iqhjeO1BREREFBxq/oSxmj+xzLoFRs199Tfror4XAQDyi/NRZa9CrCG2w22Q1bbOzOPxFvysYPJpIMNkMuHIkSNITExs8b3u3bvjZz/7GX72s59h4cKF+Prrr3HixAmfBzK6MvenO5nJTGaeR5ltTSM1aRKQlOTz4EWw++5yuTBv3jwsXboUP/zwA1599dUWawX4m+krZlJXF0rHTqi0lZnMZCYzmUmkMAlTSxmNRgkNkZ+lRJ5MrFtg1NxXf7N6x/TGgPgBOFxxGJtObMKV6VdKa0tzXalunYl1U55PU0s9++yzXgcxvLniiiswc+bMDjWqq1BiYXFmMpOZKswUAjFabcNC3t6mkcrIAGpqgI0b/boDI5h9bzyIAQBvvvkmduzY0aFMfzCTurpQOnZCpa3MZCYzmclMImUIiXeR2+122O121WUpkScT6xYYNfc1kCz39FIbjm2Q0obWdLW6dRbWTXk+r5FB/jt48CAzmcnMrp750x0YCX37AlFRQONPyZWUAGYzkJfX8D0//wAIVt+bD2JotVqsWLECY8eODTjTX8ykri6Ujp1QaSszmclMZjKTSGES7sjQ6XTQ6XQSGiM3S4k8mVi3wKi5r4FkeQYyjis7kNHV6tZZWDflSRvIKCgoQP/+/WXFERGFBqu17WmkTCbVr4PRWGuDGO6FvYmIiIiIiAIlhICQMCAiO0uJPJlYt8Coua+BZE1JnQIA2HZyG6wOq5R2eNPV6tZZWDflSRvIqKurw7Fjx2TFdQlDhw5lJjOZeZ5kAjh3B4bZ7Pc0Ut50dt8DHcQIlX10PmeS+oTSsRMqbWUmM5nJTGYSqZ/L5YLL5VJdlhJ5MrFugVFzXwPJSotLQ0pMChwuB3KKcqS0w5uuVrfOwropz6fFvgHg4YcfbvP7paWlHW5MV3PmzBnpc5gyk5nMVEGmEA13YgAN62K4mUwNX5J0Zt87cieGKvcRM0nlzpw5A9l7WaljJ1SOc2Yyk5nMZCaRwiRNLSWL7GlS1DztCusWGDX3NZAsjUaDi1Mvxvs/vo/1x9ZjWr9p0trTWFerW2dh3ZTn8x0ZL7/8MtavX48dO3Z4/dq3b5+S7QxJZWVlzGQmM7ta5k9rYiAqquWaGJJ1Zt+zs7MDnk5KdfuImRQCQunYCZW2MpOZzGQmM4kUwsW+g451C4ya+xpo1sV9lV/wuyvWrTOwbsrz+Y6MgQMH4qGHHsKvfvUrr9/Pz89vdSHY85VWq2UmM5nZ1TJbWROjZvRoREdGdqBVLXVm3+fPn48PP/wQhw8f9ntNDNXtI2ZSCAilYydU2spMZjKTmcwkaspmswFo+BS3VqtFXV0djEYjrFYrTCYTLBYLIiMjYbPZEBERAafTCSEEdDod7Ha7Zxv3fRgOhwOWykrodDoIIeByuVps6/6v0WhEbW2t55h1Op3Q6/VwOByIjIxERUWFZ1uDwQCHw4GwsDBoNBo4HA4YDAbYbLYWue5tNRoNwsLCUFdXh9raWr/71Liddrvd82lll8sFm83mV59aa6cQAmaz2a8+tbafdDodbDYbrFarX33ytp8a7wN/++RtP7W1TwM59oQQqKur86tP7e0nu93uV59a29blckGj0cBqtQb8enL/Nzw8HHa7veE15kefxiY1vPe6uWgzSs6WID4m3rOtEAI2my2g11Pj/dR4nwb6emrcJ2/HSEePvfb2qb/HXluve1+PPffzmc3mgF9PjbfV6XSwWq2efdqRc3nz131HXk/uPgkhpJzLrVbf13vx+Y6MrKwsbN++vdXvazSaLrFoiExZWVnMZCYzu1pm4/NcozUxonfskL6od2f2vVevXli3bh0+++wzvxf2Vt0+YiaFgFA6dkKlrcxkJjOZyUw63y1ZsgTDhg3DuHHjlHkCCe/52O12v960aov7DT5ZZOfJJLNtMveBEnky2Ww2qftUZp7Vag3oE/KDEwajm7Eb7PV27DizQ0pbmlPzMRJo3TqDEuckmXdkqPV16hfho9OnT4vCwkJfN1etqqoqAUBUVVUJc61ZIBsC2RDmWrP059q6dSszmcnMrpTpcgmRkSFEwyW8EOZz5w1VtdOHTKfTKWw2m9RMmZjZoPHvLApd3vbj1q1bhcjObjiXzJ8v5XmUOB6VymUmM5nJTGaqIzPhuQSBbIiC0gIhBK89ugrZ+/HYJZc0XLM891yHs2pra0Vtba2EVsnNUiJv1apV0rJYt8Coua8dybrxwxsFsiGe2fBMk8dl1a6r1q01rFtgZNXNn99ZPt+R0bNnT6SmpiozmtJFKbEaPDOZycwgZArRsKh3aSmQn9/wWEYG0GgqKVW008dM98Le11xzjZQR+VDq+/maSeoTSsdOqLSVmcxkJjOZSaR+FosFFotFdVlK5MnEugVGzX3tSNbFqQ3rZKw7tk5KW5rrqnVTGuumPJ/XyCD/JSUlMZOZzAz1TPfi3s3Xxdi4sclUUkFvp48SExMxb948z8LeM2fOxFdffQVNB6bFCpW+n8+ZpD6hdOyESluZyUxmMpOZRAqTMLWU0WiU0BD5WUrkycS6BUbNfe1I1rS0aQCA749/jzpnHSK0EbKaBaDr1k1prJvyfL4jg/yXkJDATGYyM9QzvS3uPWkSYDIFnukj2ZkulwvZ2dmeQQytVot58+Z1aBADCI2+n++ZpD6hdOyESluZyUxmMpOZROpXW1uL2tpa1WUpkScT6xYYNfe1I1nDuw9Ht8husDqs2HZym5T2NNZV66Y01k15HMhQ0P79+5nJTGaGcqZ7Sik39+Leze7G8CvTDzIz3dNJvffeewAaBjFWrFjh98Le3qi978wkNWqynw8ckPIJR6WOnVA5zpnJTGYyk5lE6qfVaqHValWXpUSeTKxbYNTc145khWnCMDVtKgBgbeFaKe1prKvWTWmsm/I4kEFE5B6waPxlNgOZmUCPHue2M5kavjp4B0Nncw9iNL4TQ9YgBhF1wEcfNfx3zRrg+eeD2xYiIiKi9kj44AURyeGeXmpd4brgNoSoE503a2QsWbIES5YsgdPpBADk5uYiTH9uHGfbtm3oHt8d/fr1w65duwAAqampcLlcOHHiBAAgIyMDhw4dgtlshslkwqBBg7Bjxw4AQEpKCrRaLY4dOwYAGDVqFCIiIpCTkwODwYDhw4dj+/btAIDk5GQYDAYcOXIEADBixAgUFRWhsrISERERyMjIwNatWwE0LLIeFRWFQ4cOAQB69+6NgwcPory8HOHh4Rg7diy2bt0KIQSSkpIQHx+PAwcOAAAGDx6M8v/P3pnHR1WdDfiZTDKZLCQkQMIawk4gQAgBVNwVUSsqiHUX19qKy6fVtta6b59abbXFuu8LVqsV/KwILghVQkLYCVsICVtCQjZmMpNl5n5/XGaywyz3JneS9/n95pfMzZ1n3vOec+/czLnnnIoKysrKCAsLY+rUqeTm5uJyuejTpw9JSUnk5+dTX19PRUUFNTU1lJaWAjB9+nTy8vJoaGggISGBgQMHsmXLFgBGjBhBbW0tBw8eBCArK4vNmzfjdDqJj48nJSWF+vp6srOzSU1NpbGxkX379gGQmZnJtm3bqK2tJTY2lhEjRrBhwwYAUlJSACguLgZg0qRJFBQUYLPZiI6OZvjw4WRnZ3vzHR4ezp49ewCYMGECxcXFVFdXY7VaSU9PJzc3F4ABAwYQHR1NQUEBAOPHj+fAgQNUVlaiHL0Q83iTk5OJi4tj586dAKSlpXHo0CEOHz6M2WwmKyuLnJwc3G43/fr1IzEx0XtX1OjRo6msrKS+vp41a9Ywbdo01q5dS2NjI4mJiSQnJ5Ofnw/AyJEjsdlslJSUADBt2jTWr19PfX09vXv3ZvDgwWzevBmA4cOHEx8f741xypQpbNmyBafTSVxcHKmpqS3arMvl8uZ78uTJ7NixA7vdTmxsLCNHjmT90cWqExMTKSkpadFmCwsLOXLkCFFRUaSlpZGXl+dtdxaLhcLCQm++9+7dS1VVFZGRkUycOJGcnBzq6+spKioiJibGm+9x48ZRUlJCRUUFERERZGZmesuSlJREfHy8N99jx46lvLyc8vJyb5t1uVxkZ2fTt29f+vbty7Zt2wAYNWoU1dXVHDp0qE2bTUxMpH///mzdutXbZu12uzffnjzU1dXROy6OUZdfTtjRHHbEkYkT2btnD8OGD2/3HFFfX09dXZ1f54g9e/ZQU1PT4TnCcxz5c45IS0ujtLTUe46YPHkyF110EV9++SWgdmI89thjDBkyhKqqKp/OEZ58d3SOsFqt2Gw2v84RmzZtAujwHFFfX8+WLVv8OkeMHTvW22bbO0c0Pyf7eo5o3WZbnyMGDRrErl27/DpHlJWVYTKZOjxH1NfXc/jwYWw2mzcmITRp79ojJiaGzMxMwsLCULZuxdMtWrZiBbtPPz2oa4+hQ4eSn59/zPOKXHvItYdcexjg2qN3b4YMGeL9LBw2bBj19fXs37/f22bz8/NxOBz06tWrw/9PjHrt0focMWDAAG/+fT1HePIt1x76X3s0NjYCUFVVRZG9SK49hPbR8EYuz3WR0Vx6+LRE8hYYRi5rsC5PR8Z/9/6XusY6IsMjtQgL6N550xPJWyegBMCKFSuUnJycFttycnKUFStWBKLrVKqrqxVAqa6uVmx1NoWHUXgYxVZn0/y9CgoKxClOcRrZ6XYrSkaGoqj3FrX/yMhQlCNH1H27Ks4AcblcyvXXX68ACqCYzWbl73//u0bRNWHEsncXZ/PPLCF0aa8eCwoKFMVkajrXXHNN0O+jR3vUyytOcYpTnOI0hjPx6USFh1Hyy/IVRZFrj+6C1vVYdPbZ6vXKU08F7XI4HIrD4dAgKm1devgWL16smUvyFhhGLmuwLrfbrfT/c3+Fh1FW7FG/j9Uqd905b+0heQsMrfLmz2dWQFNLnX766Vx77bUttl1zzTWcccYZQXWqdDfKysrEKU5xGtlZWwtH7xJl1Cg4ckSdUqr5Iy8PYmOPexeSEcteX1/vvavbM51UVlaWFqG1wIhlF6dgdEKp7YRKrOIUpzjFKU5B0BkNppZyOBw4HA4NgtHWpYdPSyRvgWHksgbrMplMTetkFGq7TkZ3zpueSN70J6CppQoLC4mIiGix7dtvv6WhoUGToLoLJh3m0RenOMWpkbP1Qt6eDotgnBoTrNNqtbJ48WIuueQSbrjhBubNm+edFkJLjFh2cQpGJ5TaTqjEKk5xilOc4hQEfVA0bHcxMTGGdOnh0xLJW2AYuaxauM5IPYNFmxfx/Z7veYiHNIhKpbvnTS8kb/pjUpSetVpTTU0N8fHxVFdXY7aaiX1K/eLSdp+NGEv3qFRBEI6DosDJJ8NPPzVts9nUhby7IYqiyD+9IUrzz6y4uLiuDkcIkA7rMSys6c7Ga66Bd9/tmgAFQRCEHkufZ/pQ4aggf0E+Y/uOlWuPboLW9Vh0zjkMXbYMnnwS7rsvKFdlZSUACQkJQcelpUsP35IlS5g9e7YmLslbYBi5rFq4dhzewZi/j8FitlD1+yqWf71ck9x197y1Rqs2J3kLDH8+swKaWkrwDc/ieeIUpziN5Vy3alXLTowZMyA6OiinEcrudrt54IEHOHDgQIvtzTsxjBCnODvfKRiPUGo7oRKrOMUpTnGKUxB0RoP7YGNiYjS7M1hLlx4+LZG8BYaRy6qFa1TiKAb2Gki9q56f9/2sSVzQ/fOmF5I3/fFpaqmEhASf7+atqKgIKqDuRGNjozjFKU6jORWF0Tfd1PS8tBT69TvuGhjHo6vL7na7uemmm3jrrbf4+OOP+eGHHxg4cGBQTl8Rp/GdgvEIpbYTKrGKU5ziFKc4BUEnNBzdbT86va/FYjGUSw+flkjeAsPIZdXCZTKZOCP1DD7Y9AHfF37PNKYFHZdWsenlk/bW9a6uxKeOjL/+9a86h9E9SUxMFKc4xWkEp6KoC3sD2O3E7Nih/p6RoUknBnRt2Zt3YgDs3r2bvLy8djsyDFtH4tTVKRiPUGo7oRKrOMUpTnGKUxCMj9VqNaRLD5+WSN4Cw8hl1crl7cjY8z3T+mnTkdET8qYHkjf98akjY/78+XrH0S1JTk4WpzjF2dXO9tbD8LBypWZ3F3VV2Vt3YpjNZhYtWsQFF1wQsNNfxGl8p2A8QqnthEqs4hSnOMUpTkHQGQ2mlmpoaAAgKirKUC49fFoieQsMI5dVK9cZw84AYM3+NTgTnUHHBT0jb3ogedOfgNbIKCgo4E9/+hNXXHEFhw4dAuA///kPW7Zs0TS4UCc/P1+c4hRnVztra9vvxJgxQ9PFvbui7B11YsybNy9gZyCI0/hOwXiEUtsJlVjFKU5xilOcgmB8wsLCCAvTZrlWLV16+LRE8hYYRi6rVq5hvYeREp9Cg7uBfLs2nxE9IW96IHnTH79LsGLFCiZMmEB2djafffYZNpsNgA0bNvDQQw9pHqAgCIJmlJaCzUbO999rOhqjKwikE0MQBEEQBEEQBKErMZlMPq/B2pkuPXxaInkLDCOXVSuXZ50MgI1HNgbt8zi7e970QPKmP353ZPzhD3/g8ccfZ9myZS0WCDnzzDNZvXq1psGFOiNHjhSnOMVpJGdMDMTEMHzCBM07MTqz7MF0Yhi+jsSpi1MwHqHUdkIlVnGKU5ziFKcg6IxGU0t5pjgxkksPn5ZI3gLDyGXV0uXpyNh0ZJMmvp6SN62RvOmP3x0ZmzZtYs6cOW22JyUlUV5erklQ3QXPaBVxilOcXehs52LbkHH64Vy0aFHAIzFCveziFLoLodR2QiVWcYpTnOIUpyDohIY3gVmtVs0WndXSpYdPSyRvgWHksmrp8qyTsat2F0fqjgTt6yl50xrJm/743ZHRu3dvDh482Gb7unXrGDRokCZBdRdKSkrEKU5xdqXT7YbMTG2dHdCZziuuuIJbb701oOmkQr3s4uyZ1NXV8eOPP/Lee+/xyiuv8Nlnn1FYWNjVYQVFm3ouLYWCgqDudNSr7YRKOxenOMUpTnEKgvFxOBw4HA7DufTwaYnkLTCMXFYtXSnxKQxPGI4bNyuLVwbt6yl50xrJm/6E+/uCyy+/nN///vd88sknmEwm3G43//3vf7nnnnu49tpr9YhREATBfxQFpkyBnTvV5xkZEB3dpSFphclk4u9//zs33ngjme101AhCd+G///0vL7zwAkuWLKGhoYH4+HiioqKoqKigrq6O4cOH86tf/Ypf//rX9OrVq6vDDY5vvoGRI+Gee+DZZ7s6GkEQBEEQhLZoMLVUTEyMBoFo79LDpyWSt8Awclm1ju2M1DPYXbmb7wu/5/xR5wfl6kl50xLJm/6YFMW/T6L6+noWLFjA22+/jcvlIjw8HJfLxZVXXsnbb7+N2WzWK1ZNqKmpIT4+nurqasxWM7FPxQJgu89GjEXbSlUURfOFVMQpTnH6iN0OserxzahRsG0bhIUF5zwGejrdbjeFhYWMGDFCM6eWiFM/Z/PPrLi4OE3fx+hceOGF5OXlceWVVzJ79myysrKIiory/n337t2sXLmSjz76iA0bNvDuu+8yc+bMLoy4Y9qrR0VRMJnNbb8QmDlT7dQIAD3ao15ecYpTnOIUpzGcfZ7pQ4WjgvwF+YztO7ZHX3t0J7Suxz3nnUfq11/Do4/CAw8E5aqsrAQgISEh6Li0dOnhW7JkCbNnz9bEJXkLDCOXVevYPtj4AVd/fjVTBkwh91e5Qbl6Ut5AuzYneQsMfz6z/J5aymKx8Nprr1FQUMCXX37J+++/z7Zt23jvvfcM34nR2axfv16c4hRnVzgVRe3I8JCX5+3ECNh5HPRyehb2zsrKYu3atZo4tUacxneGIr/4xS8oLCzkmWee4ZRTTmnRiQEwfPhw5s+fz9dff823335LWJjflzRdSii1nVCJVZziFKc4xSkIxicmJkazO4O1dOnh0xLJW2AYuaxax+ZZJyPvYB4VjoqgXD0pb1oiedMfv6eW8pCSksKQIUMAdLn7rztQX18vTnGKUw+nokBtbfsvUBQ45RRo/k9eq3NUqJTd6XRy0003eRf2Pu+88ygoKAhqCp1QKbs4hVtuucXnfceNG8e4ceN0jEZ7QqnthEqs4hSnOMUpTkHQGQ2mlrIfveHMYrEYyqWHT0skb4Fh5LJqHdvAXgMZYh3CXudeftjzA3PT5homNiPnTUskb/oT0O2Lb7zxBunp6d4Vz9PT03n99de1ji3k6d27tzjFKU6tnZ4FvGNj23/06tWyE2PGjDZrY4RC2d1uN3/+85+9nRhms5mXXnop6HUAQqHs4tTeKRiPUGo7oRKrOMUpTnGKUxCMj+d7JKO59PBpieQtMIxcVj3yNqnXJACW714elKen5U0rJG/64/eIjAcffJDnn3+e22+/nRNPPBGAn3/+mbvuuovi4mIeffRRzYMMVQYPHixOcYpTS6dnAW9fhtRnZMDKlRAT02ZEhtHL7plO6rPPPgPUToxFixYxb968oN1GL7s49XF2VzZs2EBmZiYul6urQ/GbUGo7oRKrOMUpTnGKUxBa4nA4AHUWDbPZTH19PVFRUdTW1hITE4Pdbic6OhqHw4HFYsHlcqEoChERETidTu8+HhoaGrBXVREREYGiKLjd7jb7en5GRUVRV1fnnYLc5XIRGRnJ4cOHiYqKavEaq9VKQ0MDYWFhmEwmGhoasFqtOByONl7PviaTCYfDQUNDA3379vW7TM3jdDqdREREcOTIEdxuN4BfZeooTkVRsNlsfpWpo3pyuVzU1dWRkJDgV5naq6fmdeBvmdqrp2PVaSBtT1EU6uvr/SpTR/Vks9lwu93e9uJrmTrat6qqCsAbYyDHU+s67d27d8DHU+s4J/aayJdlX/LNrm+CanvN6zTQ46l5mdprI4G2PbvdTmNjI3369An4eGqvTA6HI6Djqfm+jY2NNDQ0eP8/DeR4ar6v2+3G4XDQp0+fgI+njo77QI6n1mVSFIXKysqgz+W1Hc240g5+j8j4xz/+wWuvvcZTTz3FhRdeyIUXXshTTz3Fq6++yksvveSvrluzefNmcYpTnFo6a2ubOjFGjYIjR8Bma/+Rl6eO0Ghn6jsjl93TidF8JIZWnRhg7LKLUz9nd0bRYIqDriCU2k6oxCpOcYpTnOIUejoLFy5k3LhxTJ06VVOvouF04iaTybDTkxs9Ni1dRvZpiR5xaeXUI2/psemYTWYKqgoorikO2GPkNtKT2ltPyZs/+D0io6GhgaysrDbbp0yZQmNjoyZB6cHChQtZuHCht1csNzeXsMimfpycnBySEpIYNmwYGzduBGDo0KG43W727t0LQEZGBrt27cJmsxETE8Po0aNZt24doN4ZYzabKSoqAmDixIkcOXKE7OxsrFYr48eP9y7UO3DgQKxWK7t37wYgPT2dffv2UVVVhcViISMjgzVr1gDQv39/YmNj2bVrFwCNjY3s3LmTiooKwsPDmTJlCmvWrEFRFPr160dCQgI7duwAYMyYMVRUVFBWVkZYWBhTp04lNzcXl8tFnz59SEpKIj8/n8rKSioqKqipqaG0tBSA6dOnk5eXR0NDAwkJCQwcOJAtW7YAMGLECGprazl48CAAWVlZbN68GafTSXx8PCkpKVRWVpKdnU1qaiqNjY3s27cPgMzMTLZt20ZtbS2xsbGMGDGCDRs2AOq6KwDFxerJdtKkSRQUFGCz2YiOjsbtdpOdne3Nd3h4OHv27AFgwoQJFBcXU11d7Z3uLDc3F4ABAwYQHR1NQUEBAOPHj+fAgQNUVlZSXV0N4PUmJycTFxfHzp07AUhLS+PQoUMcPnwYs9lMVlYWOTk5uN1u+vXrR2JiItu3bwdg9OjRVFZWUllZyZo1a5g2bRpr166lsbGRxMREkpOTyc/PB2DkyJHYbDZKSkoAmDZtGuvXr6e+vp7evXszePBg7z8pw4cPx+FweGOcMmUKW7Zswel0EhcXR2pqaos263K5vPmePHkyO3bswG63Exsby8iRI70LBDqdTkpKSlq02cLCQo4cOUJUVBRpaWnk5eUBMGjQICwWC4WFhd587927l6qqKiIjI5k4cSI5OTlUVlZSVFRETEyMN9/jxo2jpKSEiooKIiIiyMzM9JYlKSmJ+Ph4b77Hjh1LeXk55eXl3jZbVVVFdnY2ffv2pW9UFPFHj9mK5cupLivj0KFDbdpsYmIi/fv3Z+vWrd42a7fbvflWFIX169d7734YMmQImzZtAmDYsGHU19ezf/9+b5vNz8/H4XDQq1evDs8RlZWV1NXV+XWO2LNnDzU1Nd5zRE5ODk8++SRffvklAGFhYTz22GOcd955bN++3adzRFpaGqWlpR2eIxoaGrz59/UcATBq1KgOzxE2mw2bzebXOcKT747OEZWVlWzZssWvc8TYsWO9bba9c0Tzc7Kv54jWbbb1OaKhoYFdu3b5dY4oKyvDZDJ1eI6orKzk8OHD2Gw2b0w9lblzjz2va3V1taEvxtq79oiJiSEzM5OamhoUoHX0dXV1HD5wIKBrD5fLRX5+fovzilx7yLWHXHsEee3Rty/btm0D1M/C6urqbnXt0foc4TmO/DlHyLVHaF97eP6Hr6qqoshe1OOvPUKdBQsWsGDBAmpqaoiPjycqKoq4uDjv36OPTrkbGRkJNM2V7nnenKioKO8+1Ue3RYSHtzu9WfN9m/9sbxqThISEFrF49vU4muN5fWuvZ1/PHcKRkZF+l6m9OD3XlVFRUX6VqaM4TSYTsbGxfpUJ2q+n2tpaoqKivH/ztUzt7du6DvwpU3v15Eud+tP2TCYTFovFrzJ1tG9YWJj3uT9l6mhfz01U0dHRAR9Pnp9a1GnrOGPDY5k2aBo/7/uZ1aWrGTdwXIf7HqueWtdpIMdTczpqI4G0PX/r1Jd6MplMfh/3HdVp87bha5k62re2thar1doiNl/L1DpOX457f9ueyWTyeoM5l/tzc6JJ8fNWxttvv52IiAief/75FtvvueceHA4HCxcu9EfX6Xg+0KurqzFbzcQ+pX6o2O6zEWPRdvX2srIy+vXrJ05xilMrp92ujrIAddRFTGDHrBHLrigKN998M2+88QagXpS/+uqr3HDDDVqFCBiz7OLs2Nn8M6v5P6E9hYiICGbOnElycnK7f6+oqODLL780/NRS7dVjWVkZ/ZKT2y6aOXMmfPNNQO+jR3vUyytOcYpTnOI0hrPPM32ocFSQvyCfsX3H9vhrj+6C1vW45/zzSf3Pf+Chh+Dhh4Nyeabm0WK9Fy1deviWLFnC7NmzNXFJ3gLDyGXVOjZQc5cTm8NjPz7GFelX8OElHxoitlDImxZtTvIWGP58Zvk0IuPuu+/2/m4ymXj99df55ptvOOGEEwD1jrLi4mKuvfbaIMLufjidTnGKU5xaORVF7cjQ0qkhwTpNJhNTpkzhjTfe8E4nNX36dI2ia8KIZRen/s5QJS0tjUsuuYQbb7yx3b+vX7/eO4Ip1AilthMqsYpTnOIUpzgFQR+0nFqqvbt1jeDSw6clkrfAMHJZ9crb2cPP5rEfH2P57uW4FTdhJr9XFeiRedMCyZv++NSa161b531s2rSJKVOm0K9fPwoKCigoKKBv375kZmZ6h/YKKgcOHBCnOMWphVNR4OSToYO7sgNyaowWzt/85jf84x//8K6JYdQ4xRl6zlBlypQp3ik72iMyMtI77UeoEUptJ1RiFac4xSlOcQqC8amtrfVrYdfOcunh0xLJW2AYuax65e2EwScQHRFNWW0Zmw8Ftq5ST8ybFkje9MenERnff/+93nEIgiB0jN0OP/3U9HzGDGg152B34de//nVXhyAIhuHll18+5rRRaWlp3vnzBUEQBEEQBJ3xb2bydokJcHpgvV16+LRE8hYYRi6rXnmzmC2cNvQ0/rPrPyzfvZyJyRP9dvTEvGmB5E1//B9fJPjMlClTxClOcQbrzMyEU05p2lBaCitXQhDDm41QdrfbzS233MKnn36qmdMXxNkznaFKZGRkm4XSuguh1HZCJVZxilOc4hSnIBgfu92OXaMpg7V06eHTEslbYBi5rHrm7ezhZwOwfPfygF7fU/MWLJI3/QmoIyM3N5ff/e53XH755cydO7fFQ2hCj6m2xCnOnubMX7sW1q9Xn2RkQL9+QXViQNeX3e12c9NNN/Hqq69y+eWXd9iZ0dVxirP7OAXjEUptJ1RiFac4xSlOcQqC8YmOjtbsRhUtXXr4tETyFhhGLqueefN0ZKwoWkG9q97v1/fUvAWL5E1//O7IWLRoESeddBL5+fl8/vnnNDQ0sGXLFr777jvi4+P1iDFkCZXF3cQpzpBxBjkSo12nRvjq9HRivPXWW5o5/UGcPdMpGI9QajuhEqs4xSlOcYpTEHRGg6mlHA4HDodDg2C0denh0xLJW2AYuax65i09KZ2kmCRqG2pZvW+136/vqXkLFsmb/vjdkfHkk0/yl7/8hSVLlmCxWHjhhRfYtm0bv/zlL0N2wU29iIuLE6c4xRkkvWJjm55o0IkBXVf21p0YZrPZu7B3oE5/EWfPdArGI5TaTqjEKk5xilOc4hQEndDo/zAAi8WCxWIxnEsPn5ZI3gLDyGXVM29hpjDOGnYWAMsKlvn9+p6at2CRvOmP3x0ZBQUF/OIXvwDUJNjtdkwmE3fddRevvvqq5gGGMqmpqeIUpziDwe1m9BVXaOuka8rubyeGL85AEGfPdArGI5TaTqjEKk5xilOc4hQE4+NyuXC5XIZz6eHTEslbYBi5rHrnzbtORqH/62T05LwFg+RNf/zuyEhISODIkSMADBo0iM2bNwNQVVVFbW2tttGFOBs3bhSnOMUZKG43jB1L2K5d6vOMDNBoPr/OLnsgnRjHcwaKOHumUzAeodR2QiVWcYpTnOIUpyDojAZTSymKgqKBR2uXHj4tkbwFhpHLqnfePB0Za/avodpZ7ddre3LegkHypj9+d2SceuqpLFumDku69NJLufPOO7n55pu54oorOOusszQPUBCEHoiiwJQpsHOn+nzUKFi7VtMhzZ1FoJ0YgiC05N133+WLL75ose2LL77g3Xff7aKIBEEQBEEQegaKhv+HRUREEBERYTiXHj4tkbwFhpHLqnfeUuJTGN1nNG7FzQ97fvDrtT05b8EgedMfvzsy/v73v3P55ZcDcP/993P33XdTWlrKJZdcwhtvvKF5gKHM0KFDxSlOcQZCbS2sXw9A4/DhsG0bhPl9uuqQziz71q1b+eijjwD/OzEMXUfiDClnd+C6667jvvvua7Ht97//Pddff30XRRQcPtWzwwF79oCPQ4D1ajuh0s7FKU5xilOcgmB8nE6nZovWa+nSw6clkrfAMHJZOyNvZw87Or3Ubv+ml+rpeQsUyZv+hPv7gsTERO/vYWFh/OEPf9A0oO6EHnOPiVOcPcLZbLjbof/8h4EadmJA55Y9PT2dL7/8kjlz5vDmm2/6NRLD0HUkzpBydgfcbnebbdu2beuCSLThuPV85AgMGwaHD8Opp8KKFcE7AyRU2rk4xSlOcYpTEHRGg2lJYmJiNAhEe5cePi2RvAWGkcvaGXk7e/jZvJT7kt/rZPT0vAWK5E1/fPp2sKamxueH0MS+ffvEKU5x+oKigN2uPmw2yMz0/mn/gQMaRddEZ5f9rLPOorCw0O/ppAxVR+IMaadgPPbt2wd//nPHOxQVqZ0YALm5vjt1IFTauTjFKU5xilMQdELDqaXsdjt2u91wLj18WiJ5Cwwjl7Uz8nZ66umEmcLYVr6NfTW+f3709LwFiuRNf3wakdG7d29Mx/ngUhQFk8kkd4gIguAfbre6HsbRqaRakJGB22rt9JCCwe1283//93/Mnj27xfY+ffp0UUSCEJr4c3NEXFycjpHoyN13q50ZBw92dSSCIAiCIAidgpHvMDbyHcuSt8Awclk7I28JUQlkDcxizf41LN+9nOsyrvPpdT09b4EiedMfnzoyvv/+e73j6JZMnjxZnOIU57HwLOrdQScGa9cyubFRi9BaoFfZmy/s/cgjj/Dggw8G7dQacfZMZyjS3W+iCKW2EyqxilOc4hSnOAVBZzSYWspzR7DFYjGUSw+flkjeAsPIZe2svM0cPpM1+9ewtGCpzx0ZkrfAkLzpj09TS5122mk+P4QmduzYIU5xirMjFAXKypo6MUaNUueEt9nUR14ehIV1fZw+sm3bNm8nBsCjjz5Kfn5+UM5QKbs4je8MRb7//nu+++67Yz48+4QiodR2QiVWcYpTnOIUpyAYn6ioKKKiogzn0sOnJZK3wDByWTsrb7NGzAJgWcEyXG7fbgCTvAWG5E1//F7sW/AdPeYeE6c4u4VTUeDkk+Gnn5q25eVBbGzgTj/Q2ul2u7n//vv58ssvATCbzSxatIi0tLSgvKFQdnGGhjMU6e43R4RS2wmVWMUpTnGKU5yCYHycTicAVg2mENbSpYdPSyRvgWHksnZW3k4YfAK9LL047DhM3sE8pg6a2umxhWLeAkHypj8+jcgQAiO2nS9lxSlOcQK1tS07MWbMgA7m6zN62T3TSbXuxPB3Ye/2MHrZxRk6zu7AypUrufrqqznppJPYv38/AO+99x6rVq3q4sgCI5TaTqjEKk5xilOc4hQEndFgaqmIiAgiIiI0CEZblx4+LZG8BYaRy9pZeYswR3D28LMBWFqw1LfXSN4CQvKmP9KRoSMjR44UpzjFeTxKS2HlSuhgLnzDxNkOzdfEAG07McDYZRdnaDlDnX/961/MmjWLqKgo8vLyqKurA6C6uponn3yyi6MLjFBqO6ESqzjFKU5xilMQdOI465b5g6IoKBp0iGjt0sOnJZK3wDByWTszb57ppXztyJC8BYbkTX96zNRSCxcuZOHChd4FQXNzcwmLbOrHycnJISkhiWHDhrFx40YAhg4ditvtZu/evQBkZGSwa9cubDYbMTExjB49mnXr1gEwePBgzGYzRUVFAEycOJH//ve/9OrVC6vVyvjx41m7di0AAwcOxGq1snv3bgDS09PZt28fVVVVWCwWMjIyWLNmDQD9+/cnNjaWXbt2AdDY2EhSUhIVFRWEh4czZcoU1qxZg6Io9OvXj4SEBO+8qWPGjKGiooKysjLCwsKYOnUqubm5uFwu+vTpQ1JSEvn5+VRWVjJt2jRqamooLS0FYPr06eTl5dHQ0EBCQgIDBw5ky5YtAIwYMYLa2loOHjwIQFZWFps3b8bpdBIfH09KSgo//vgjCQkJpKam0tjYyL59+wDIzMxk27Zt1NbWEhsby4gRI9iwYQMAKSkpABQXFwMwadIkCgoKsNlsREdHY7PZCAsL8+Y7PDycPXv2ADBhwgSKi4uprq7GarWSnp5Obm4uAAMGDCA6OpqCggIAxo8fz4EDB6isrKS6uppzzjmH7OxsAJKTk4mLi2Pnzp0ApKWlcejQIQ4fPozZbCYrK4ucnBzcbjf9+vUjMTGR7du3AzB69GgqKyvZsWMHiYmJTJs2jbVr19LY2EhiYiLJycneNRNGjhyJzWajpKQEgGnTprF+/Xrq6+vp3bs3gwcPZvPmzQAMHz6cLVu2eOeymzJlClu2bMHpdBIXF0dqamqLNutyubz5njx5Mjt27MButxMbG8vIkSNZf3RNCqfTyZgxY1q02cLCQo4cOUJUVBRpaWnk5eUBMGjQICwWC4WFhd587927l6qqKiIjI5k4cSI5OTlUVlaSlpZGTEyMN9/jxo2jpKSEiooKIiIiyJw8mbU//siUo8deRV0dO4+297Fjx1JeXk55ebm3zf7www/07t2bvn370rdvX7Zt2wbAqFGjqK6u5tChQ23abGJiIv3792fr1q3eNmu32735VhQFq9VKXV0dvXv3ZsiQIWzatAmAYcOGUV9f773jOzMzk/z8fBwOB7169fKeI9xuNy+++CKLFi0CICwsjPfee4+0tDSys7N9Okfs2bOHmpqaDs8Ra9euJSEhwa9zRFpaGqWlpR2eIw4cOODthff1HOHJd0fnCJvNxvTp0/06R3jy3dE5Yv/+/QwZMsSvc8TYsWO9bba9c8RPP/3kPSf7eo6IiIggMzOzw3NEQ0MD/fv39+scUVZWhslk6vAcUVlZydSpU7HZbN6YejqPP/44L7/8Mtdee633mAOYMWMGjz/+eBdGdmzau/aIiYkhMzOTH3/8kbi4ODIbG2l+X0xdXR2HDxygfONGJno21tZS8stfUv7gg8c8r7hcLhISEo55XpFrD7n26JHXHs3O40lJScTHx3vzHUrXHp58e/4/qays5IwzzvDr/xO59pBrj9bniMbGRgCqqqooshfJtYegO26325AuPXxaInkLDCOXtTPzNmuk2pHx896fqXZWE2+NP+b+krfAkLx1AkoANDQ0KMuWLVNefvllpaamRlEURdm/f79y5MiRQHSdSnV1tQIo1dXViq3OpvAwCg+j2Opsmr/X6tWrxSlOcTbH7VaUk05SFHVQsvqwHfvYM2rZ7733XgVQAMVsNitPPvmkBpG1xKhlF2fnOZt/ZvVkoqKilMLCQkVRFCU2NlYpKChQFEVRCgoKlMjIyC6MzDfaq0dvPQ8Y0PKcOHOmun3NmpbbQT2HHgM92qNeXnGKU5ziFKcxnIlPJyo8jJJflq8oilx76MGKFSuUCy64QBkwYIACKJ9//vlxX+N0OpU//vGPSkpKimKxWJShQ4cqb7zxhs/vqXU9Flx4oXot8oc/BO2qra1VamtrNYhKW5cevsWLF2vmkrwFhpHLqnVsinLs3I3+22iFh1H+tfVfx/VI3gJD8hYY/nxm+T21VFFRERMmTOCiiy5iwYIFlJWVAfD0009zzz33aNW/0i0YMmSIOMUpTlC/grPboays7doY0dGBOYNAC+dNN93EgAEDvNNJzZ8/X4PIWmLUsosz9JyhTv/+/b13/jZn1apVDB8+vAsiCp5j1vPhwzBtmrbOIAiVdi5OcYpTnOIUjIjdbmfSpEksXLjQ59f88pe/5Ntvv+WNN95g+/btfPTRR4wZM0bHKI+NouHUUk6n07vorJFcevi0RPIWGEYua2fnzTu91K7jTy8leQsMyZv++D211J133klWVhYbNmygT58+3u1z5szh5ptv1jS4UMczFYE4xdmjnYoCJ5/csgMD1LUx+vU77nyrRi376NGj+eGHH9i6dSsXX3yxd+oILTFq2cUZes5Q5+abb+bOO+/kzTffxGQyceDAAX7++WfuueceHnjgga4OLyCOWc9Hpw/R1BkEodLOxSlOcYpTnIIROe+88zjvvPN83v/rr79mxYoV7N69m8TERECdEq27EBMTY0iXHj4tkbwFhpHL2tl5mzViFn9b8zeWFixFURRMx/guRvIWGJI3/fH7KmjlypX86U9/wmKxtNiemprqnddVUPHMRytOcfZoZ21t206MGTN86sTo0BkkgTjdbrd3DmEPo0eP5uKLLw7YeTzEKU5B5Q9/+ANXXnklZ511FjabjVNPPZWbbrqJW265hdtvv72rwwuIDut52TJ45x1tnUESKu1cnOIUpzjFKXQHFi9eTFZWFs888wyDBg1i9OjR3HPPPTgcjq4OTb1JLUjsdjt2u12DYLR16eHTEslbYBi5rJ2dt9NTT8ditlBUXcSOwzuOua/kLTAkb/rj94gMt9vtXbSyOfv27aNXr16aBCUIQjeltBRiYtTppDQcnqw3brebm266idraWt5//33Cw/0+dQqCEAQmk4n777+fe++917uo7bhx44iNje3q0PTh5Ze7OgJBEARBELqI3bt3s2rVKqxWK59//jnl5eXceuutHD58mLfeeqvd19TV1VFXV+d9XlNT01nh+o2R7zA28h3LkrfAMHJZOztvMZYYTk45me8Kv2NpwVLG9O14ujrJW2BI3vTHpCj+dalfdtllxMfH8+qrr9KrVy82btxIv379uOiii0hJSenwg9Uo1NTUEB8fT3V1NWarmdin1C9BbPfZiLFoW6kOh4OoqChxirNnO+128HzZaLOpHRnBOoPEH6enE8Nzbrv66qt57733DBenOLuns/lnVlxcnKbvE6rs3bsXCK05wturR289DxwIBw/6JnK7j9kJrEd71MsrTnGKU5ziNIazzzN9qHBUkL8gn7F9x8q1h86YTCY+//xz76ju9jjnnHNYuXIlJSUlxMfHA/DZZ58xb9487HZ7u/X/8MMP88gjj7TZvmjRIqKPsyahL6S9/jojFy9m19y55F93XVAuz1dQx5rWpitcevjcbrdm08FJ3gLDyGXVOjY4fu4+K/2Mt/e/TVZcFg+OfLDTYgv1vPmK5C0wamtrufzyy3279vB3JfG9e/cq48aNU9LS0pTw8HDlhBNOUPr06aOMGTNGKS0t9VfX6TRfCd1WZ1N4GIWHUWx1Ns3fa8uWLeIUZ89zut2KYrM1PUpLFUUdhKw+N0qcPuByuZTrr79eARRAMZvNyieffBKU0x/EKc7mn1k9mYaGBuVPf/qTEhcXp4SFhSlhYWFKXFyccv/99yv19fVdHd5xaa8evfU8YEDTOfJ4D7f7mO+jR3vUyytOcYpTnOI0hjPx6USFh1Hyy/IVRZFrD70BlM8///yY+1x77bXKiBEjWmzbunWrAig7duxo9zVOp1Oprq72Pvbu3atpPe66+GL1WuR3vwva5XA4FIfDoUFU2rr08C1evFgzl+QtMIxcVq1jU5Tj525DyQaFh1Gin4hWnA3OTost1PPmK5K3wPDn2sPv+VEGDx7Mhg0bWLRoERs3bsRms3HjjTdy1VVX6XIXYChz5MgRcYqzZzlratpf2DsYZxeVvfVIDLPZzKJFi5g3b17ATn8RpzgFldtvv53PPvuMZ555hhNPPBGAn3/+mYcffpjDhw/zj3/8o4sj9J9QajuhEqs4xSlOcYpT6A7MmDGDTz75BJvN5p1Gc8eOHYSFhTF48OB2XxMZGUlkZGRnhhkwnimwrFaroVx6+LRE8hYYRi5rV+RtQtIEBsQO4KDtIKuKV3HW8LM6JbZQz5uvSN70x++ODKfTidVq5eqrr9Yjnm6FHh074hSnYZ2KQqzD0XEnxowZ6toYftIVZfe3E8MXZyCIU5yCyocffsiiRYs477zzvNsmTpzIkCFDuOKKK0KyIyPgev7qK/jiC0hLgzvvbDHVlF5tJ1TauTjFKU5xilMwIjabjV27dnmfFxYWsn79ehITE0lJSeG+++5j//79vPvuuwBceeWVPPbYY1x//fU88sgjlJeXc++993LDDTd0ff1rsNi32WzWIBDtXXr4tETyFhhGLmtX5M1kMnHOiHN4Z8M7fL3r6w47MiRvgSF50x+/J7JKSkpi/vz5LFu2DLfbrUdM3Ya0tDRxirNnOBUFTj6Z8Wee2bSttFRdE8PzWLkyoAW+O7vsgXRiHM8ZKOIUp6ASGRlJampqm+3Dhg3DYrF0fkAaEHA933gjvPoq3HUX7NihjfM4hEo7F6c4xSlOcQpGJDc3l8mTJzN58mQA7r77biZPnsyDD6rz0x88eJDi4mLv/rGxsSxbtoyqqiqysrK46qqrmD17Ni+++GKXxA+gaDinuiAIXcusEbMAWFqwtIsjEQT/8bsj45133qG2tpaLLrqIQYMG8T//8z/k5ubqEVvIk5eXJ05x9gxnbW3LkRgzZkC/furC3p5HgBe/nVn2QDsxjuUMBnGKU1C57bbbeOyxx7zDYUEdGvvEE09w2223dWFkgeNTPQ8fDpde2nJbbW37v/vqDIBQaefiFKc4xSlOwYicfvrpKIrS5vH2228D8Pbbb/PDDz+0eM3YsWNZtmwZtbW17N27l+eee67rR2NohMvlwuVyGc6lh09LJG+BYeSydlXeZo6YiQkTmw5t4sCRA+3uI3kLDMmb/vg9tdScOXOYM2cOR44c4dNPP+Wjjz7ihBNOYPjw4Vx99dXeuwoEQeihlJaqnRgheNeOzWZjw4YNgH+dGIIgaM/cuXNbPF++fDmDBw9m0qRJAGzYsIH6+nrOOqv94dDdhpdegk8+6eooBEEQBEEQNJlaSsu1PLReF8TI64xI3gLDyGXtqrz1je7LlIFTyD2QyzcF33BdxnVt9pG8BYbkTX/8HpHhoVevXlx//fV88803bNy4kZiYGB555BEtYwt5Bg0aJE5x9ignENToi/bozLLHxcWxfPlypk+f7ncnRqjUkTh7pjMUiY+Pb/G45JJLuOCCCxgyZAhDhgzhggsuYO7cucTHx3d1qAERSm0nVGIVpzjFKU5xCoLxcTgcOBwOw7n08GmJ5C0wjFzWrszbuSPOBTqeXkryFhiSN/3xe0SGB6fTyeLFi/nwww/5+uuvSU5O5t5779UytpBHj3m7xSlOQzo1uDOnIzq77AkJCfz000+EhfnXz2v4OhJnj3aGIp4p3rorPtVzXJz2zgAIlXYuTnGKU5ziFATjExMTY0iXHj4tkbwFhpHL2pV5O3fkuTy+8nGW7lqKy+3CHNZyIWjJW2BI3vTH7xEZS5cuZf78+SQnJ/Ob3/yG5ORkvvnmG4qKivjf//1fPWIMWQoLC8Upzu7vdLshM1MbVzvoWXa3281TTz1FVVVVi7/724nR3Kkl4hSn0H3xqZ5fe017ZwCESjsXpzjFKU5xCoLOaHADm91ux263axCMti49fFoieQsMI5e1K/M2ffB0EqwJVDorWb1vdZu/S94CQ/KmP35/WzdnzhwcDgfvvvsuJSUlvPLKK5x66qkBB7Bw4UJSU1OxWq1Mnz6dNWvWHHP/qqoqFixYwIABA4iMjGT06NF89dVXAb+/IAgBoihgs8HYsbBzJwD20aMhOrqLA/MNz8Lef/zjHznnnHPadGYIgmAsPv30U375y19ywgknkJmZ2eLhLyFz7ZGV1fL5Cy9ATY3+7ysIgiAIgtAcDacOjomJ0ezOYC1devi0RPIWGEYua1fmLTwsnFkjZwHw1c62/9dI3gJD8qY/fndklJaW8s9//pOLLrqIiIiIoN78448/5u677+ahhx4iLy+PSZMmMWvWLA4dOtTu/vX19cycOZM9e/bw6aefsn37dl577TXDzhM6YcIEcYqzezoVBU4+GXr18nZiMGoUprVrNV/kW4+yjx8/nptuusk7dU1eXh7Z2dlBOQ1XR+IUZzfixRdf5Prrryc5OZl169Yxbdo0+vTpw+7duznvvPP8chnl2iOgev7977V3+kCotHNxilOc4hSnIBgfI99hbOQ7liVvgWHksnZ13s4feT4AX+1q25EheQsMyZv++NSRUdPs7j9FUaipqenw4Q/PP/88N998M9dffz3jxo3j5ZdfJjo6mjfffLPd/d98800qKir497//zYwZM0hNTeW0005j0qRJfr1vZ7F3715xirN7Ou12+OmnpucZGbBtG3v37w86rtZoXXa32838+fO9nRhms5lFixYxa9asoLyGqyNxirMb8dJLL/Hqq6/yt7/9DYvFwu9+9zuWLVvGHXfcQXV1tV8uo1x7BFTPjY3aO30gVNq5OMUpTnGKUxB0RoOppaxWK1arVYNgtHXp4dMSyVtgGLmsXZ23c0eeiwkT60vWs7+m5Xc5krfAkLzpj08dGQkJCd47FXv37k1CQkKbh2e7r9TX17N27VrOPvvspmDCwjj77LP5+eef233N4sWLOfHEE1mwYAHJycmkp6fz5JNP4nK5fH7fzkSPqWrEKc4ucyqK2oFhs7VcE6O0FPLyICzMGHEeA890Up999hnQ1Ikxb968oN1GL7s4e7Yz1CkuLuakk04CICoqiiNHjgBwzTXX8NFHH/nsMdK1R0D17HarPzsY+aZX2wmVdi5OcYpTnOIUBH1QNBx139DQQENDg+Fcevi0RPIWGEYua1fnrV9MP6YNmgbAf3b9p8XfJG+BIXnTn3Bfdvruu+9ITEwE4Pvvv9fkjcvLy3G5XCQnJ7fYnpyczLZt29p9ze7du/nuu++46qqr+Oqrr9i1axe33norDQ0NPPTQQ+2+pq6ujrq6Ou9zf0eNBENkZKQ4xRnaTkWB2lr15ymnwPr1Lf+ekQH9+nm/VDNy2T2dGK1HYmjRiQHGLrs4xRnq9O/fn4qKCoYOHUpKSgqrV69m0qRJFBYWovhxZ6CRrj18rmc/Okz0ajuh0s7FKU5xilOcgmB8wsL8nuG8U1x6+LRE8hYYRi6rEfJ2/qjzyd6fzVc7v+KmzJu82yVvgSF50x+fOjJOO+007+/Dhg1jyJAhmFr1yCuKovswV7fbTVJSEq+++ipms5kpU6awf/9+nn322Q6/THjqqad45JFH2mzPzc0lLLKpEnNyckhKSGLYsGFs3LgRgKFDh+J2u73lysjIYNeuXdhsNmJiYhg9ejTr1q0DYPDgwZjNZoqKigCYOHEiFouF7OxsrFYr48ePZ+3atQAMHDgQq9XK7t27AUhPT2ffvn1UVVVhsVjIyMjwLjzav39/YmNj2bVrFwBjx45l586dVFRUEB4ezpQpU1izZg2KotCvXz8SEhLYsWMHAGPGjKGiooKysjLCwsKYOnUqubm5uFwu+vTpQ1JSEvn5+SiKQkVFBTU1NZSWlgIwffp08vLyaGhoICEhgYEDB7JlyxYARowYQW1tLQcPHgQgKyuLzZs343Q6iY+PJyUlBafTSXZ2NqmpqTQ2NrJv3z4AMjMz2bZtG7W1tcTGxjJixAg2bNgAQEpKCqDeeQswadIkCgoKsNlsREdHk5aW5l3HYPDgwYSHh7Nnzx5AnSu2uLiY6upqrFYr6enp5ObmAjBgwACio6MpKCgA1PURDhw4QGVlpXedF483OTmZuLg4dh5d9yEtLY1Dhw5x+PBhzGYzWVlZ5OTk4Ha76devH4mJiWzfvh2A0aNHU1lZidPpZM2aNUybNo21a9fS2NhIYmIiycnJ5OfnAzBy5EhsNhslJSUATJs2jfXr11NfX0/v3r0ZPHgwmzdvBmD48OEkJiZ6Y5wyZQpbtmzB6XQSFxdHampqizbrcrm8+Z48eTI7duzAbrcTGxvLyJEjWX+0M2Lw4MGUlJS0aLOFhYUcOXKEqKgo0saMoX7iRGKOtqfWONPS2PDSS0Ru2MDEiRPJyclBURSKioqIiYnx5nvcuHGUlJRQUVFBREQEmZmZ3rIkJSURHx/vzffYsWMpLy+nvLzc22YbGhrIzs6mb9++9O3b1/tl46hRo6iurvaOFmveZhMTE+nfvz9bt24F1PPWbbfdxieffAKonRhPPfUUQ4YMYfv27QwZMoRNmzZ5962vr2f/0WmyMjMzyc/Px+Fw0KtXrw7PEYqiUFdX59c5Ys+ePdTU1HR4jvAcR/6cI9LS0igtLe3wHJGSkuLNv6/nCE++OzpH9O7dG5vN5tc5wpPvjs4RTqeTLVu2+HWOGDt2LHl5ed58tz5HREZGes/J/pwjmrfZ1ueIMWPGsGvXLr/OEWVlZZhMpg7PEYqicPjwYWw2mzemns6ZZ57J4sWLmTx5Mtdffz133XUXn376Kbm5ucydO1fX99b62iMmJobMzExMJhPZ2dmk3HgjAx5/vF1PdnY2k6OisLTargAm4NChQ7ibncfT09PJz88/5nlFrj3k2sPQ1x5pad7z+KBBg7BYLBQWFnrzvXfvXqqqqoiMjDT8tceIESOw2+3efE+ZMoX169dTV1dH79695dpDrj0Mc+3ReHTawqqqKorsRXLtIRwbDaaWav1dklFcevi0RPIWGEYuqxHydv6o83noh4dYtnsZ9a56LGb1Pw/JW2BI3joBxU/CwsKU0tLSNtvLy8uVsLAwnz11dXWK2WxWPv/88xbbr732WuXCCy9s9zWnnnqqctZZZ7XY9tVXXymAUldX1+5rnE6nUl1d7X3s3btXAZTq6mrFVmdTeBiFh1FsdTafY/eV1atXi1OcoeV0uxXFZlOUI0cUZdQoRVEvVZseGRnq32w2dd+uitNPXn75ZQX1uz/FbDYrTz75pAaRtcSoZRdnaDurq6u9n1k9GZfLpTQ0NHiff/TRR8rtt9+uvPjiix1+/reHEa49PLRoO263osya1facqyiKkp/fdrvJpP7My2vxvnq0R7284hSnOMUpTmM4E59OVHgYJb8sX1EUufboLmhdjzsuuUS99rjrrqBdlZWVSmVlZfBBaezSw7d48WLNXJK3wDByWbWOTVH8z53L7VKSn01WeBhlecFy3WLrbnnrCMlbYPjzmeX3uBJFUdrtxbHZbH4tGmKxWJgyZQrffvutd5vb7ebbb7/lxBNPbPc1M2bMYNeuXbg9c0QDO3bsYMCAAVgsre9XVImMjCQuLq7FQxCEdlAUOPlkiI2FXr3g6F1fjBoFR46oa2Pk5al/j4npcI52I3LDDTcwb94873RSZ555ZleHJAiCH4SFhREe3jSI9PLLL+fFF1/k9ttv7/Dzvz0Me+0RQudTQRAEQRCEYDDy4rVGXgxX8hYYRi6rEfIWZgrjvFHnAfDVzq+82yVvgSF50x+fppYCuPvuuwF1KMoDDzxAdHS0928ul4vs7GwyMjL8evO7776b+fPnk5WVxbRp0/jrX/+K3W7n+uuvB+Daa69l0KBBPPXUUwD85je/4e9//zt33nknt99+Ozt37uTJJ5/kjjvu8Ot9O4v+/fuLU5yh47Tb4aefWm7LyIC1a8HHufSMWvaIiAg+/PBD1qxZw4wZM7xTLGiJUcsuTnGGKp5pVHxh4sSJPu9rlGuPoOo5LKzdtTP69+8PGzfCvfeqnSPPPAN+5KYjQqWdi1Oc4hSnOAVBZzSYWsrhcABo8oWali49fFoieQsMI5fVKHk7f+T5vL3+bb7a9RXPzXoOkLwFiuRNf3zuyPDMtaooCps2bWpxF6LFYmHSpEncc889fr35ZZddRllZGQ8++CAlJSVkZGTw9ddfexfhLC4ubrEYyZAhQ1i6dCl33XUXEydOZNCgQdx55538/ve/9+t9O4uYmBhxitP4TkVROzEyM5v+WFqqjrqIjvbrTmGjlN3tdlNSUsLAgQO92yIiIpgxY0bAzuMhTnEa2RmKZGRkYDKZjruYt8lkwuXHgthGufYIuJ5/8Qt1dNzReeDbOF98Eb75Rt2Qng5//nMQUTbzaow4xSlOcYrTOE5BOC4ajh7Vsg1rfTwY+fiSvAWGkctqlLydM+IczCYz28q3sbtyN8MThkveAkTypj8+d2R8//33AFx//fW88MILmk3RdNttt3Hbbbe1+7cffvihzbYTTzyR1atXa/LeelNQUEDfvn3FKU7jOvv0UaeTaj4SIyMD+vUL6GLVCGV3u93cdNNNfPPNN/zwww+MHDkyaKcviFOcRnaGIp4FfvXACNceAdfzq6/C1KkdO48u2gpA89+DIFTauTjFKU5xilMQjI/dbgfwa3rQznDp4dMSyVtgGLmsRslbvDWek1NOZkXRCr7a+RW3TbtN8hYgkjf98bkjw8Nbb72lRxyCIHQFtbVtOzHWrg3Z+do9nRie89TMmTPJz88P+aFzgtATGTp0aFeHIAiCIAiCIDRHg6mljHyHsZHvWJa8BYaRy2qkvJ0/6vwWHRmSt8CQvOmPTx0Zc+fO5e233yYuLo65c+cec9/PPvtMk8C6A+PGjROnOEPHWVoa8EiMDp0a4KuzdSeG2Wzm2WefbbcTI2TrSJziFLoNurSdtDRYv157b4i0c3GKU5ziFKcg6ISGN7oZ+Q5jI9+xLHkLDCOX1Uh5O3/U+fx++e/5fs/31DbUUmevAyRv/iLtTX98WsE3Pj4e09EPrvj4+GM+hCZKSkrEKc7QccbEBH2B2lVlb68TY9GiRcybNy9gp7+IU5xGdgrG45j17HY33fFoNvvsrHv0UfjxxyAja0uotHNxilOc4hSnIBgfq9Wq2Yh5LV16+LRE8hYYRi6rkfI2vt94UuJTcDY6+b7we8lbgEje9MenERnNp5OSqaV8p6KiQpziNLZzwADtnRpzPKe/nRi+OANBnOI0slMwHses5+adyu2s89MR7h072tnohhUroKICzj4bArjpJFTauTjFKU5xilMQdEaDqaUaGhoAiIqKMpRLD5+WSN4Cw8hlNVLeTCYT5488n5fXvsxXO7/ilP6nAJI3f5H2pj8+jchojsPhoLa21vu8qKiIv/71r3zzzTeaBtYdiIiIEKc4jesMD4dTTtHW2cllD6QT43jOQBGnOI3sFIyHz/VsMkFlZcttni8Rjl6MeggLC2t6DYDdDt98A2eeCfPmwa23Nu3sckFVlU9fSIRKOxenOMUpTnEKgj4oGk4tZTKZvDN+GMmlh09LJG+BYeSyGi1v5486H4Cvdn0FIHkLAGlv+mNSFP+61M855xzmzp3Lr3/9a6qqqhgzZgwWi4Xy8nKef/55fvOb3+gVqybU1NQQHx9PdXU1ZquZ2KdiAbDdZyPG0j0WPhGE46IoUFYGycnq84wMyMsLqUW+FUXhxhtv9LsTQxBCieafWXFxcV0dTpdSVVXFp59+SkFBAffeey+JiYnk5eWRnJzMoEGDujq8Y+JTPZ57Lixdqv7e+tKsqgoSEtTf9++H5uUtL4c+fdTfb7wR3nyz5WtPPbVpuqnTT4fvvwenE8aPh927YeZMtbND6JmsWwe//CVYLPD738O113Z1RIFTVgbbt8PgwZCSAmFh6rH05Zfw9deQmgp33+3XdG2C0BPo80wfKhwV5C/IZ2zfsXLt0U3w1GNJSQlRUVGYTCbMZjP19fVERUVRW1tLTEwMdrud6OhoHA4HFosFl8uFoihERETgdDq9+5TdcgujP/mExltvxfbEE0RERKAoCm63u82+np9RUVHU1dVhPnredblcREZGUllZSXR0NG6327uv1WqloaGBsLAwTCYTDQ0NWK1WHA5HG69nX5PJRH19PQ0NDSQkJPhdpuZxOp1OIiIiqK2txe12ExcX51eZOopz2bJlnHnmmX6VqaN6MplMOJ1O4uLi/CpTe/V0+PBhbx34W6b26ulYdRpI21u2bBnnnnuuX2XqqJ6cTicul4v4+Hi/ytTRvkeOHMFkMhETExPw8eT5CVBXV0evXr0CPp5ax/n1118zc+bMgI4np8vJkL8Poc5Vx/fzvmfy4Mm43e6Aj6fmZaqqqmrTRgJte06nk8bGRnr37h3w8dS6TN9//z0zZ84M6HhqXaf19fXehbUDOZ6a7xsWFkZtbS29e/cO+Hjq6LgP5HhqXaaVK1dyyimnBH0ut9vtDBgwwKdrD79HZOTl5XHK0bu4P/30U/r3709RURHvvvsuL774or+6bk12drY4xWk8p9sNmZlNnRgAK1dq0onR2WUfMmQI4H8nhuHrSJziFFqwceNGRo8ezdNPP82f//xnqqqqAPjss8+47777uja4APGrnptPB9V6SsANG9Sf5eVtOzGg/TUziorUTgxQOzaOQ6i0c3H6gc0Gc+ao1wO7dsHWrfDyy7BmDXzwAezd29b5f/8H8+fDI4+o1xKdEacP5P3f/6mddElJ6kjTYcPUzoqnnlI7My68EF56CX73O/jnP+H55+G11+Crr2DWLPX6x2RSj7MPPtAtTnGK08hOofuwcOFCxo0bx9SpU/V5A42mlqqvr9cgGNXV0GqEqpF8WqJlbFrWgR4+LTFyGzFae4uxxHDKYPX73q8LvzZsGzFa3prj6Vw1os/Ix6k/+LRGRnNqa2vp1asXAN988w1z584lLCyME044gaKiIs0DFARBQ9xuGDsWdu5s2jZjhrrQd4hhMpl4+OGHCQsLY/z48TISQxC6MXfffTfXXXcdzzzzjPcaBOD888/nyiuv7MLIOgmTqemL49adzmedpY7SePzxzo9LCE2+/BJmz267/eefYfp09feRI4l85hn1i//XX4dly1rue955MG2a/rGCOg3am2/Ck0+qnRVPP612XOzdC3PmkLl2bfuv++Mf22471vmipgauvhp+/BHLL36hSeiCIAidzYIFC1iwYIF3REZUVFSLu1ujo6MBiIyMBMBisbR43hzPPOoWi4Wyo9cf4eHh9O7d+5j7Nv/Z3sKyyUdvqGsdQ3vztnte39rb+v0iIyP9LlN7cYaHh3tf60+ZOorTZDIRGxvrV5mg/Xqqq6sjLi6uTbn8idOzb+s68KdM7dWTL3XqT9szmUxYLBa/ytTRvp7p+CIjI/0qU0f79u3b1+sL9Hjy/Kyrq2t3/2DanslkIioqKqDjCWDu+LksL1rOipIVPBL3iDe2QI6n5nTURgJpe/7WqS/11Dpvgba9juo00LbX/LgP9Hjy57j3t+2ZTCYSjs4cEMy53J/JovwekTFy5Ej+/e9/s3fvXpYuXco555wDwKFDh2ToaSuSkpLEKU7jOFt1YjSkpsKRI5qNxoDOL7vJZOKhhx7yuxPDsHUkTnHq5Ax1cnJyuOWWW9psHzRoECUlJV0QUfD4Xc+eu8bbY+NGOHzYN4/LBddd13Z7SQksXqxOzdMKv2PdtUt1HTjQ4S6hcux0K2d5OUyc2LYT4+i1fAt27SJj7ly47LK2nRigdnj86U/qyIb6erX9/OlPcP/9cPBgcHGCOp3a5ZerbT48HH71K9izRx0xcsYZ6vaUFGjeiTFhgroeTGvef9+39/Tw6qtMvugiGDNG7dyprlZHPpWXt38nss2mTll14olwwQWwYwd8+il8/rk6jdtRulVbEme3cwpCZ1JbW9ti3VWjuPTwaYnkLTCMXFYj5m32GPU6MXt/NkXl2t2s3t3z5kHam/743ZHx4IMPcs8995Camsq0adM48cQTAXV0xuTJkzUPMJSJbz4VhDjF2ZVORYEpU5pGYowaxZGcHIiN1XRdDD3L7na7WbBgAT/88INmTi0RpziN7Ax1IiMjqampabN9x44d9OvXrwsiCh7d6vlvfzv23zdvhtWr224/5RS46CK1w7u8vMWf/Iq1pkZ1XHTRMe/YD5Vjp9Ocn36qrlsyYwYUFGjjBHXB9y+/hNtug379YNOmpr/97/+qHVuvv+7bm7S+aeCJJ9QOht691SnPnnhCHTVxjDZ43HzabOpaLwkJ8PHHPoXVmJGhjs7YuBG+/VZ9nHMO3Hmnev1z1VVNO594oto5A3DDDVBXp3bEfPRRW/GOHXDSSWr5MjLU/IWFqddN/fvDJZeov/fqBX/5i3pc/d//qR0gl14Kc+eqo0IaG30rewCIU5yC0OloMLVUTEyMd/54I7n08GmJ5C0wjFxWI+ZtcNxgJvefjILCioMrNPN297x5kPamP353ZMybN4/i4mJyc3NZ6lmUEjjrrLP4y1/+omlwoc7O5tP3iFOcXeX0LOy9fr36fNQo2LaNnQF8UXI89Cq72+3mpptu4qWXXuL8888PujPDcHUkTnHq7Ax1LrzwQh599FHv/KAmk4ni4mJ+//vfc8kll3RxdIGhaz0fa/Fzl6vl88ZGSE9XR1F4OHSoxS7F332nfin8u9+16eRow3/+0/Qe+/d3uFuoHDu6Oxsb1cW2L71UXafip5/U+mgvzxUV6pfrd9yhfoE+cqS6xsns2ST26dM0aufWW9UOBpNJvWFh9mxYuLDJk5Skjpb5/e/VL+aHDFGvFdzuprVTmrNihTrC5pNPYPTotn93OFo+f+qp9kdxtC67h3371I4CT6dAe2u9zJ+v5qc1Bw6w9uWX1QW+PZx5JixdCn/9a9M2RVFHR/z0EyxapD5/4w11kfOICHX0h6JATk67cbehtBQ+++z4+/3lL6r/3XeP35b27VOd+flq/bTOazto3j7Lytjz88+g8bzTIXls9jCnIBwXDW9+s9vt3kVxjeTSw6clkrfAMHJZjZq3C8dcCMDibYs1c/aEvIG0t87A7zUyAPr370///v3Zt28fAIMHD2ZaZ82TKwiCbyiKeifmKac0dWIA5OWpX1yECJ5OjLfeegtQFzsqP94XaYIgdCuee+455s2bR1JSEg6Hg9NOO42SkhJOPPFEnnjiia4Or+upqFDXMvCwYQMcnb+3De11BG/Zckz9wPffhy++UJ88+yzcfLP6BW3rO3oOHlS/EBZ848CB9judnE717v/jUVDQ/lRK//hHx6959VW46ab2v5AymdSFsvPyYNAgsgsLme5ZM8PD9u1w7rlqR8GxeOMNdSRoYmLTtro6IsrL1Q6TsDCorFQ7KJYsad+xapU6QqU57d0JXFx87Fg8tDNncBuyskBRWLNyJdNOPbVp+y9+oY62aI+xY9VRL9XVapnbY/58BixYANnZ6qilSy6BtDS1I+tf/2r/uImPVzuu+vVTOzd69VI7nZoRVlurTiuXkwPffad2gs2Zo+7bEZ5pRSsq1LVGevVS19j5858ByPTs9847cO21HXsEQeiZaDAiwzO3uxZo6dLDpyWSt8AwclmNmrfZo2fzyIpH+K74O5yNTqzhbddH8JeekDeQ9tYZ+N2R4Xa7efzxx3nuueew2WwA9OrVi9/+9rfcf//9hIXQF6R6M3bsWHGKs2ucbrf6z3TzDgxosbC3IeI8Dm63m4ULF/LBBx8AYDabWbRoUdALe4dC2cUpTqGJ+Ph4li1bxqpVq9i4cSM2m43MzEzOPvvsrg4tYNrUc6uFIP3it79t+t1igT591LvXx41rud+2be13ZHTEN9/A00+T9N13Lbe/9pr6+OEHOO20pu2fftq+x9OxHhUFZjMQOseObs6ff1anLepMdu9WOyqOx9GpYsd29MX/11+rP2fNUtvI/ffDo4+qowkuvVT928cftzs1VCaoa1xkZamdYu3x+efq1GQ+3v2rRx2NmTix4y/r3nlHHcH06KNqp0TzaX48r6mqgltuadHBmNJ8VMwDDxw/iOpqtS6arzVz+ulqbmJi4LbbmFpf3/Z177+v1tG336odLA6H6qmqgsce82mkBwDLl3fckVFQAPfeq/5+0klwzz3HVIXUsdlDnYJwPBQNR2Q4jp6H2luUtitdevi0RPIWGEYuq1HzljkgkwExAzhoP8j3hd9z3qjzgnb2hLyBtLfOwO9eh/vvv5+///3v/O///i/r1q1j3bp1PPnkk/ztb3/jAV8uynsQetw1Lk5xHhNFUeeXHju2ZSdGRkabhb2NXnbPSAytOzHA+GUXpziFluzduxeAk08+mVtvvZXf/e53Id2JAe3Us2canKeeOv6L585t+bz5VFBz5qg/09Ka1kOYObPtfsf54hGA559X7/LuiNNPVzsyvv5a/WL3jjvU7dZmd20pirq2Qq9eMGKE+hlF6Bw7ejidr73WshNj+nT1y+WjuTku0dHwyCNNz19+md0bN6r10HwUQV2d2nmhKOrDl06MZhy37EuXqt7HH1dHWMybB6mpxxd//33LToxBg9T244nz4ov9msKk0+t9/ny1Q8BkatmJ0ZzevdWOnHXrfH/TP/2p7UiK5p0YoHYe3nWXOnVYe50YoE7rZTar64S8+KLa6Xjrrep6HcfqxDCZ4Jlnmp6vX6+2oX/+Ux2F9dvfqiNTPNOaff65+rj3XjVuz9RmzR+XXQaHD4fMsdmTnYLQmVgsFiwWi+Fcevi0RPIWGEYuq1HzZjKZ+MXIXwCweLs200v1hLyBtLfOwO+OjHfeeYfXX3+d3/zmN0ycOJGJEydy66238tprr/H222/rEGLoEioXruLsJk63GzIz1X8mmy3qzZEj6jQRrRb2NnLZW08npWUnBhi77OIUp3xB0ZbU1FROO+00XnvtNSorK7s6HE1oU8+DB6tf4v7hD8d/8b/+1e7mgj/9qeWUROnpLRc7drvVn2PHNt1N3RFud9tRfe3x44/ql6XNR2M8/XTT72FhTWsJFBWp6zKMHk2/Sy9Vp8TREMMcjxUV6loScXHql8fNue8+kpvn/r771NEZVqt6l/3mzU1/+/Zb9TP8zTfVDqOff24a3fLgg+pr33sPbrmFstpadYTEihVNHQIWi9+dF80JqOyzZvm3f26uujbEiBH+v9dRDFPv7ZGRoa438cgj1GRktD8iKi9Pra/HHlNHeLQeCdK/f4f6sl/8Ql0kfvFiWLDAt5h++1t1RIXHe+ed6ugPtxvuvVeNE9SOUKtV7Yx4/XW1Y/Orr9p3dtQJ989/wmefqfmsrlaPjeZUVqrXrJ5zkx8Yut5D0CkIPqPB1FIulwtX6zW7DODSw6clkrfAMHJZjZy3WcPUa7olO5agdPPjXkukvemP31NLVVRUtDucdezYsVS0vjg1EAsXLmThwoXeSsvNzSUssqkfJycnh6SEJIYNG8bGjRsBGDp0KG6323snaEZGBrt27cJmsxETE8Po0aNZd/ROq8GDB2M2mykqKgJg4sSJ2Gw2srOzsVqtjB8/nrVr1wIwcOBArFYru48uqJiens6+ffuoqqrCYrGQkZHBmjVrAHU9ktjYWHYdXYTT5XKxc+dOKioqCA8PZ8qUKaxZswZFUejXrx8JCQns2LEDgDFjxlBRUUFZWRlhYWFMnTqV3NxcXC4Xffr0ISkpifz8fCorK6moqKCmpobS0lIApk+fTl5eHg0NDSQkJDBw4EC2HJ1De8SIEdTW1nLw4EEAsrKy2Lx5M06nk/j4eFJSUqisrCQ7O5vU1FQaGxu966lkZmaybds2amtriY2NZcSIEWzYsAGAlJQUAIqPznU8adIkCgoKsNls3rncsrOzvfkODw9nz549AEyYMIHi4mKqq6uxWq2kp6eTm5sLwIABA4iOjqbg6OLW48eP58CBA1RWVlJdXd3Cm5ycTFxcnHcRvbS0NA4dOsThw4cxm81kZWWRk5OD2+2mX79+JCYmsn37dgBGjx5NZWUllZWVrFmzhmnTprF27VoaGxtJTEwkOTmZ/Px8AEaOHInNZqOkpASAadOmsX79eurr6+nduzeDBw9m89EvM4YPH47T6fTGOGXKFLZs2YLT6SSuVy9Sk5LYvGkT6fPnE3W0rQLYR48mYsMGduzahd1uJzY2lpEjR7L+6BdTdXV1lJSUtGizhYWFHDlyhKioKNLS0sjLywNg0KBBWCwWCgsLvfneu3cvVVVVREZGMnHiRHJycqisrKSoqIiYmBhvvseNG0dJSQkVFRVERESQmZnpLUtSUhLx8fHefI8dO5ZDhw5x99138+WXXwIQFhbGY489xuTJk6murmbbtm0AjBo1iurqag4dvcO4eZtNTEykf//+bD26MOiIESOw2+3efJtMJtavX09dXR29e/dmyJAhbDp65/KwYcOor69n/9FFajMzM8nPz8fhcNCrV68OzxGVlZXU1dX5dY7Ys2cPNTU1HZ4jPMeRP+eItLQ0SktLOzxHNDY2evPv6znCk++OzhF2ux2bzebXOcKT747OEZWVlWzZssWvc8TYsWO9bba9c0Tzc7Kv54jWbbb1OcLlcrFr1y6/zhFlZWWYTKYOzxGVlZUcPnwYm83mjamnk5uby4cffsijjz7K7bffzrnnnsvVV1/N7NmzDT00tr1rj5iYGDIzMzly5AjZ2dnHPK9Ax9cekf/6FxlHFzpXAE83dX5+fpvzyoiPPqL5ihkOhwN3TAyVr77K4F/9qk3cBw4cIPHJJ7EePd4B3FYrYU5nu+V05+UR9p//AOAaNYoDY8YwpN09gZdeAiAOOPLllxw+7bRude2xZdEiJl59tbe4dW+9Rf6UKYy124m49VbMzRbY2/b881SfdBLJRUUtrz2OfrYdPnwY87ZtZF1/PTnp6ep5ZffupvPKRRep55Xduzv32iMujtTU1BZt1uVyqfm+/nom3347OxQFR3k5k+fORXn2WTYOGoQSFkbW0Y6O/L/9jZqpU5k4bhyFW7d2+bVHeXk55eXl3s/CqqoqsrOz6du3L3379g3+2mPWLEznnovFYqFu9eqW1x719Qw7dKjFtceUV17B9dhjbHznHWL692d4WBjVf/wjh2fOZNytt1LxxhvsHD+eyspKzjjjDHbt2oX9l79kWrPpqza/+SaJM2YQUV5O5YoVuK1Whv761+q1R1kZ1q+/brr2yM/3XnvU9+lDXEfHL1DXvz81Dz1E2Jw59DlGJ4uXX/2K5iutKOHqv5+mxkbvtpqsLI6kpzPo7bdxp6RQNnUqe+69V649Ounao/FoXVRVVVFkL5JrD0F3tPhSVA+XHj4tkbwFhpHLauS8nTrkVKLDo9l/ZD/rStaROSDz+C86Bj0lb9Le9Mek+FmS6dOnM336dF588cUW22+//XZycnJYvXq1pgFqTU1NDfHx8VRXV2O2mol9Sp2T2nafjRhLzHFeLQgGQlHg5JPhp59abh81Sr27LybGr6kZjMLq1auZMWMGbrdb85EYghBqNP/Mios71ldLPQNFUfjhhx/48MMP+de//oXb7Wbu3Lm8+eabXR3aMdGtHqdMUc/3Ht56C667ru1+8+a1HMVxwQVNCyy73erogbIy9Q7+8nJ14eBbb1V/erjiCvjwQ/Xu6dGjO47pk0/UtTnGjz9+/J9+qi56HOo0NKhrEXzwQYejZdqwd686CqenYberd/kfXStFMCjPPgu/+526uPhPP6nXlIcOqc+bLxRpt6uL0/fp07TNs5i7VtegL76o+lNT219XRlHUqVPfew8SEtRpt0aO1Oa9ewh9nulDhaOC/AX5jO07Vq49ugla1+P2K65gzKJF6vVB8zV/AsAzT3tUVFTQcWnp0sO3ZMkSZs+erYlL8hYYRi6r1rGBdrlzOBxc9vllLNm5hIdOe4iHT384aB/0jLyBtDd/8eczy++ppZ555hnefPNNxo0bx4033siNN97IuHHjePvtt3m2o0X7eig5zb8AEKc4tXba7W07MTIy1MVcW00j5bMzSLRwnnDCCXz44YdERkayaNEihg4dqkFkLTFq2cUpTr2c3QWTycQZZ5zBa6+9xvLlyxk2bBjvvPNOV4cVEHrU8+6jd64fl+bTQIWFqesTHB2hCMDUqU2dGE88weFzzlGnlgG1szw5uX3v5Mlqp0kXLUR7zJwWF6trL5xzDqxapY0T1M/ic85R1y1p3onhWaukNZmZ5Pz0k+adGKFyLsrZulXzToyQKXsoOe+9V+0gKC5W22pCAowZ07ITA9QOjuadGKCeU0DtXDgevpwr7rhDnR5vxgz46CN1PaFp03AMG6Ze64aFqVOvvf662gHz2GM+lbM9QqqOBKGr0OCOXqfTibODUZ5d6dLDpyWSt8AwclmNnrdzhp4DqNNLaeHrKXmT9qYvfk8tddppp7Fjxw5eeukl71D1uXPncuuttzJw4EDNAwxl3AHM9ypOcfrkVBQ45ZSm56Wl6j+T0dE+3wFn5LJfdtllnHLKKQwcONA7rF5LjFx2cYpTD2d3Yd++fXz44Yd8+OGHbN68mRNPPJGFQd4V2FXoUc82XzsQ/JmO68QT2XXWWfRp/gVmR3fxeNZ+CAtTP6e++w7OOgsSE1vOjR8ZqS4irDEd5rSsTB1F4nnPxET1S9H2Pi8VBVwu9ct2k4moLVvUNT5SUuCWW5q+pAV1fv/Jk9W1P5rzwQeq5/PP2/rXrsUtn2vi7AnOk0/2rteSvWYN06dPVzsRTzqp6Thyu9URXCecAC+/rI7WOdZ17JVXen/t8F7Cd99VH0OHquek5muH2GywdSts2QJr1sDGjepaPenpkJJC1MSJ6nmiXz91zbklS9TF7I9OQQWoo1J+/Wt1IfYVK9R1bRIS1IXQ33uvTTiGriNB8AcNR/rHxGg3E4aWLj18WiJ5Cwwjl9Xoebt43MXcsfwO8g7msa9mH4PjAr8Rpyflzag+I+fNH/zqyNizZw/Lli2jvr6eyy+/nPT0dL3i6hb07dv3+DuJU5yBOGtrmxZhzchQ/+Hy8+LSKGV3u938+OOPnH766S22ezpGjRKnOMUZys5Q55VXXuHDDz/kv//9L2PHjuWqq67iiy++0GXEVmeheT1/+CEx06a1/7ezzvJtyqMjR1o+j42FU0+l79H53pu/FyedBBER6rRKoHYMXHFFy/3OPLPpzk3PZ1R8vDrtVOsRhRrQbk5ra+Hss1t2nHz8sToF1hNPNC2u7nRCSQnMn68uYH6UFle6kyap5V6/Xp1a4+ef277fPfeoX7YuX960bcUKOPXUY8cZJOIUp2GdJlOT8+STW/4tLEwdSdyc5nd7L1+udn488kjH/sxMdVq9Bx+EL75o2l5UBHfdpR5/n3567LvIj64n4dN/tnv3wv33t9xWWQnvv68uun7GGfA//wNHr2tDoo4EoZOxH10vymKxGMqlh09LJG+BYeSyGj1vMcRwwuAT+Hnfz3y540t+nfXroHzQM/IG0t70xOeppb7//nvGjx/PLbfcwu23305mZibvv/++nrGFPKFy4SrOEHMqijqVhYeVKwO6Q8YIZXe73dx0003eqWK0cPqCOMXZ05yhzuOPP8706dNZu3Ytmzdv5r777gvpTgzQoZ4jIjp2/uY36hd9oH4Z3xGtR0nceSeYzW29J56ofhadeWbTtuuv9y3Ozz/XbX2ENnEqijqK4uii1C1wu9V1LcrK4L//hb59YdiwFp0YbThyRO2AmTy5bSdGcbH6fp5pVs8+W83fkiUtOjHajVMDxCnObuk8+2x4+GE4eFCdUurPf1ZHTDmdVFdVqcfc2rUwcSK015Hb0KB2WgY7Fc7FF3f8t+afRTU1amfKGWeoIzZoVfaCAvjHP9TO4KPzVAeCXCcIXYoGU0vFxMRodmewli49fFoieQsMI5c1FPJ24ZgLAVi8fbEmPi0IhbwZ0WfkvPmDzx0ZDzzwADNnzmT//v0cPnyYm2++md/97nd6xhbybGt9h5E4xRms07PAd/P5yQMc5tvVZfd0Yrx19Mu1BQsWUNR6eg4/nb4iTnH2NGeoU1xczDPPPMOkY30JH2J0etu57jr1M8Qzms8Xjn4B71OsN9547L+/+aY6UuGMM9r+bf9+9Q7mMWPUhX1ra32PsRlt4vzLX9S7pD20nhLrv/+FpCT1c7X5DQId8e236siT1ngWQW7NX/+qLqx+vDg1QJzi7NbO/v3VjsHf/lYdxREZ2db5xz+qozAURT3ftMdzz6nnwPXrvdNe0dgI//kPDB3KhkWL4N//Vs9DDzwAns6Szz9v2v+zz9QOUJdLfd56xJqHQYPAZCK+d2/1Wt1kUhchv/VWdc2Pl14KOB1ynSB0BYqGU0vZ7XbvncFGcunh0xLJW2AYuayhkLfZo9WFnL8r/A5bvS1on5axGRFpb/rj89RSmzdv5qeffmLAgAEAPPvss7zyyiscPnyYPq0XeRMEQR9qa1tOxzFjRtuFF0OA1p0YZrOZDz/8MOTvsBYEQTs2btxIeno6YWFhbNq06Zj7Tpw4sZOiMhglJfp4X3lFXdS7vU6H5vz617B0advFftvj+uubRm3k5ak/H3wQzjsP/vY3eOEFddudd6pfEvqzYG9xMSxfTpzDAdOnq9vef1/90tPDmjXqe3zwwfF9ubnqwsEvv4xz0CCs+/er2z2jLUCdrqumRv1Ss18/32MVBEE/UlLUn9ddp3ZWnHUWzJ597Jt+zGY491zYswdndnbTOaQj5sxpu635Heq+ftl7zz1QXq52wPTqBTt3quf0kSPVDpn4ePU8HO73kpaCYHiiOlprq4tdevi0RPIWGEYuayjkbVzvcQxPGM7uyt0sK1jGnLR2Pgf98GkZmxGR9qY/Pl8Z1dTUtBjGGh0dTVRUFNXV1dKR0QGjRo0Spzj1c5aWBrQ2xjGdQeKLs71OjEWLFjFv3ryAnf4iTnH2NGcokpGRQUlJCUlJSWRkZGAymVCafVnkeW4ymXC5XF0YaWBoUs9Hpy4BwGLRru2kpLToxOjQe/HF6t3M/k4V5bkTaOtWtXPjn/9s+ffHH1fntk9MPLbnyBHYsAHOOQccDtJAnZe+tBSuuaZpv6VLYepU9S7tgQMhO7v9KaSKitRRG/36wZQp8I9/UFtRgbX1de4DD6jT3YT5PLC5BaFy3hCnOEPWaTI1dY5q5fSVnBx1+qjt29VRX6CO2Nq7F374wbt2BgD/+7/qoyNOOaXdc5VcJwhdigZTSzmdTgCsVquhXHr4tETyFhhGLmuo5O3C0Rfy1+y/8sX2LwLuyOiJeTOaz8h58we//gNbunQpixcv9j7cbjfffvtti21CE9XV1eIUZ/AoCjUHD6pf/DQfBhYTE3AnBnRN2f3txPDFGQjiFGdPc4YihYWF9Dt6p3thYSG7d++msLDQ+/A83717dxdHGhia1/NZZwXv9EyDNGtWi83H9Aa73kXrTgwPDz10/NeeeKL6RV/zuebT09W7sD28+aba0QFgscAzz7QcWQFqx0d9vdqB02p0RZuyX3aZuvBwgJ0Y7To1QJziFKdBnFlZ8MYb6iLlikLh7t1Na+icdlpT54YvrFwJw4erI9SaxSbXCUKoExERQUREhOFcevi0RPIWGEYua6jk7aKxFwGwZMcSGt2NQfu0jM1oSHvTH7/+C5s/fz4XX3yx9+FwOLjlllu8z+e0N9S2B3Po0CFxijM4jq6JkZqeDrGxLdfGCJLOLnsgnRjHcwaKOMXZ05yhyNChQzEd7awtKipi0KBBDB06tMVj0KBB7a6tEwpoWs933gkxMcE7lyxRP3dadZJ3Spu8//6Wz8vL1Z+HD0N+Phy9g8jLLbfAli3Hdv7mNzB/ftvt06ap5ayoUBf9TkqCDi7qDx06pL7311/Dyy/DRx8FdROB16kx4hSnOEPEedJJ6vln8+ambZMnq1NhzZ4NTz+tdoR4KCxUp+HzrLVxySUcOnhQ8zgFoTNRFKXFKFujuPTwaYnkLTCMXNZQydvJKSfTJ6oPFY4KfixqZ1Sznz4tYzMa0t70x+eODLfbfdxHKE7tIAiGpvWaGB5CcG2Mu+66y+9ODEEQBIAzzjiDioqKNturq6s543jrOAjGo6Gh7bZf/xp++cuW23btgr59Ydw4dconk0kdhXHiifDqq8d/nz//+dgjJxISfOuUiIxUR6ncckvQnRiCIAgAjB/ftIB4Xh5MmgSLF8Pvfte0nlB7fPYZ02fMUM+DJpN6bnz66ZYj04SguOGGG8jOzu7w72vWrOGGG27oxIgMhgZfgnm+P9ICLV16+LRE8hYYRi5rqOQtPCycC8dcCMDn+Z8H7dMyNqMh7U1/Ah8XLxyX6cdbLE6c4vSH0lKw2dTHypVBf5nS2WW/6qqriI+P97sTI1TqSJziNLIz1PGshdGaw4cPExMT0wURBU8otR3Nva0Xr/3kExg8GD7+GK64Qt1ms8GZZ7Z97erV6sPD0qXwr3+pC4Y3Z/t2TTr8Q6WexClOcXYjp8nU1MlRUaEuDN4az3nQ6YQ//EE9Dwqa8Pbbb1NQUNDh3wsLC3nnnXc6MSKDoGFHvpGnSjHy1CuSt8AwcllDKW9zxqoz8Px7+78Duqu/p+bNSD4j580ffOrIWN38H8bjUFtby5bjDfXvIeTl5YlTnIGjKG3XxPA8NLiQ7OyyT5s2jW+++YZ//vOffo3EMHQdiVOcIeIMVebOncvcuXMxmUxcd9113udz587loosuYtasWZx00kldHWZAhFLb0b1NXnxx0+/Tpqk/v/xSXRz3WHz8sbr+xdy5cNtt5K1d2/Tl3+jRmoQWKvUkTnGKs5s6ExLUdX0UpeM1hQCuuQYyM9V1fHbsCO49hWNy4MABoqKiujqMkMbpdHoXnTWSSw+flkjeAsPIZQ2lvM0cMZOYiBj21exj7cG1Qfu0jM1ISHvTn/Dj7wLXXHMNw4cP56abbuL8889v9+7HrVu38v777/PWW2/x9NNPM378eM2DDTUa2ps6QZziPB6eDoxTTlHny9UJvcvudrsxmUwt7qKeNm0a0zxfUgXg1ApxirOnOUOV+Ph4QB2R0atXrxZfHFgsFk444QRuvvnmrgovKDSt59hY7Z3N0KWd9+5NRFUVLFrUcoTG5z4OV7/uujZTUYXK8ShOcYpTnAFx6aWgKKxZtYppJ5+sbmt+c9O6deojNVWdbgqgqEhdc2jSpLaj4QQvX3zxBV988YX3+auvvsry5cvb7FdVVcXy5cuZOnVqZ4ZnLDSYWkrL0bRaj8w18khfyVtgGLmsoZQ3a7iV80adx6dbP+Xz/M/JGpgVlE/L2IyEtDf98elqZuvWrfzjH//gT3/6E1deeSWjR49m4MCBWK1WKisr2bZtGzabjTlz5vDNN98wYcIEveMOCRITE8UpTv9wu2HKlDYdGI7MTKI0XhNDz7J7Fvbu1asXf/3rX9udEsZfp5aIU5w9zRmqeNbVSU1N5Z577uk2F1+gUT3fdRf85S/qtCJaOdtBD++eNWsYlZradpHt1qMw3n1XXRx35MiW24+2jeaEyvEoTnGKU5zBkJCc3PTk6qvh/fdb7vDMM+qjOVdfDe+9p3ks3YWtW7fyySefAGAymcjOzmbt2pZ3HJtMJmJiYjj11FN5/vnnuyLMrkXDqaXsR2cdsFgshnLp4dMSyVtgGLmsoZa3OWPnqB0Z2z7nibOeCNqnZWxGQdqb/vjUkREREcEdd9zBHXfcQW5uLqtWraKoqAiHw8GkSZO46667OOOMM+TLl1b0799fnOL0HUVp24mRkQErV9Lodmu+wKheZfd0Yni+gAwPD+e5554Lyqk14hRnT3OGOg899FBXh6A5mtTz88+rDy2d7aBbO29vjtapU6GwsOn5NdeoP0tLITERfvhBXQC8M+MUpzjFKU6jOt97r6mDjL9wHwABAABJREFUIiICGhvbf9H776uPl1+GW27RPKZQpqamhnvvvZf77rsPgLCwMN544w2uvPLKLo6s+2LkO4yNfNOM5C0wjFzWUMvbL0b9goiwCPLL89levp0xfccE5dMyNqMg7U1//B5fmpWVRVaWf0OIeipbt27VfNE4cXZjZ21tUyfGqFGQl+ddD2NrdrZx4jwGmzdv5rXXXvN2YpjNZk488cSgnIaqI3GKM0SdoUhmZibffvstCQkJTJ48+Zgju0JxXZFQajudGusHH6idGZs3wwMPNG1PSlJ/nn22MeIUpzjFKU6jOR99FP74R/X3BQtg40Ywm9UOYA8PPAAnnKCOArdaYfhwTWMLRRISEnjvvfe8HRfz589nxIgRXRyVdjgcDkAdUWI2m6mvrycqKora2lpiYmKw2+1ER0fjcDiwWCy4XC4URSEiIgKn0+ndx7O4b2NjI7aqKiIiIlAUBbfb3WZfz8+oqCjq6uowm80AuFwuIiMjOXToEFarlYiICO++VquVhoYGwsLCMJlMNDQ0YLVacTgcbbyefU0mEzabjYaGBpKTk/0uU/M4nU4nERERVFVVoSgKffr08atMHcWpKAo2m82vMnVUTw0NDTidTvr27etXmdqrp5KSEm8d+Fum9urpWHUaSNtTFIX6+nq/ytRRPdXU1OByuejXr59fZepo38OHD2MymUhISAj4ePL8rK+vp76+nsTExICPp9ZxKoqCw+EI6HhqXk+lpaXeOm1eplOHnMq3Rd/yz03/5LaM23xue2VlZW3aSKBtz9c69bftORyOgI6n5vvW1dXR0NBAQkJCwMdT8309x32/fv0CPp46Ou4DOZ5al0lRFCorK4M+l9fW1vr8uSYTZQqCEcnL8855Hiq43W6efPJJvvzyS0DtxFi0aJFfC3sLgiB4uOiii4iMjATg4uaLQQvdm/BwuOeero5CEAQh9LjvPvXRnIYGGDOmaaRbWZk64tvD8OEkXu3GXQe4XJ0VqaGwWCzU1dV5n7/77rvMnDkzZG8qWbhwIQsXLsSldX1qODtAZGQkVqtVkxitVithYWEaRNXkc7vdmvm0xNMxogVa1oEePi2JjIzUNC6r1aqpK5hpuPWkozq9YOQFfFv0LYt3Lua2jNuC9gWC1WqlsaMRiF1MVFSU5uckox73XYV0ZOiIHndyiLOHOFt9mBk2zqN4ppPSoxPD6GUXpzhDwRmKNJ9OqjtOLRVKbSdUYhWnOMUpTnG2IiICdu+Gb76BWbPa/n33bnY+evTXi4ogebw2QYYQY8eO5fXXXyc1NZX4+HgURWHPnj3HHe2ZmZnZSRH6x4IFC1iwYAE1NTXEx8cTFRVFXFyc9+/RR9dd9Nws4pkr3fO8OVFRUd59So5uCzeb6d279zH3bf6zvS996+rqUBTFe8eyZ1+Pozme17f2evatrq7GarUSGRnpd5nai9Pz5WhUVJRfZeooTpPJRGyrGxSPVyZov548ZY1utXamP3F69vV8OeqpA3/K1F49+VKn/rQ9k8mExWLxq0wd7etyuQgPD8dqtfpVpo72ra+v95Yn0OPJ87O6uprIyMg2U/4E0/ZMJlOL9utLmdqrp9ZtxFOmyyZdxt3f3k3uwVxqzbUkWBJ8irO+vr7dNhJI26uursZsNvtcp77UU+u8Bdr2PHUayHHf3r6e4751nQbS9nw57v1te57RSf6Uqb19/ems0a6bSGiDZyEVcYqzOztbr4mh9UgMI5ddnOIMFWeos3fvXvbt2+d9vmbNGv7nf/6HV199tQujCo5QajuhEqs4xSlOcYqzA845B+bPhz/8AfLzISdH87hClaeeeorNmzdz9tlnM3XqVEwmEw888ABTp05t95GVlcXUqVO7OuyuQ4M7g81ms3eKEiO59PBpieQtMIxc1lDM24BeAzhh8AkA/Hvbv4P2aRmbEZD2pj89ZkRG6yGWubm5hEU29ePk5OSQlJDEsGHD2LhxIwBDhw7F7Xazd+9eADIyMti1axc2m42YmBhGjx7NunXrABg8eDBms5mioiIAJk6cyM6dO71zkI0fP561a9cCMHDgQKxWK7t37wYgPT2dffv2UVVVhcViISMjgzVr1gDqYm6xsbHs2rULUO8QqK+vp6KigvDwcKZMmcKaNWtQFIV+/fqRkJDAjh07ABgzZgwVFRWUlZURFhbG1KlTyc3NxeVy0adPH5KSksjPz6eyspJevXpRU1NDaWkpANOnTycvL887t9vAgQPZsmULoN4FVFtby8GDBwF13ZTNmzfjdDqJj48nJSWF/Px8SkpKSE1NpbGx0fsFVGZmJtu2baO2tpbY2FhGjBjBhg0bAEhJSQGguLgYgEmTJlFQUIDNZiM6OhqbzUZJSYk33+Hh4ezZsweACRMmUFxc7O2tTE9PJzc3F4ABAwYQHR1NQUEBAOPHj+fAgQNUVlZSXV3N0KFDyc7OBiA5OZm4uDh27twJQFpaGocOHeLw4cOYzWaysrLIycnB7XbTr18/EhMT2b59OwCjR4+msrKSHTt2UFpayrRp01i7di2NjY0kJiaSnJxMfn4+ACNHjmxRnmnTprFx/XomHW2PdrudzZs3AzB8+HAKCwu9+06ZMoUtW7bgdDqJi4sjNTW1RZt1uVzefE+ePJkdO3Zgt9uJjY1l5MiRrD+6DofT6SQyMrJFmy0sLOTIkSNERUWRlpbmvRNp0KBBWCwWCo8OS58wYQJ79+6loqKCp59+mi+++AJQF8f729/+xumnn+7N6bhx4ygpKaGiooKIiAgyMzO9f0tKSiI+Pt6b77Fjx1JeXk55ebm3zW7bto2SkhL69u1L37592bZtGwCjRo2iurqaQ4cOtWmziYmJ9O/fn61bt3rbrN1u9+bQM49fXV0dvXv3ZsiQIWzatAmAYcOGUV9fz/79+71tNj8/H4fDQa9evTo8R1RWVtK/f3+/zhF79uyhpqamw3OE5zjy5xyRlpZGaWlph+eIAwcOePPg6znCk++OzhE2m40+ffr4dY7w5Lujc8T+/fux2Wx+nSPGjh3rbbPtnSOan5N9PUe0brOtzxENDQ00NDT4dY4oKyvDZDJ1eI6orKwkNjYWm83mjamnc+WVV/KrX/2Ka665hpKSEs4++2zS09P54IMPKCkp4cEHH+zqENulvWuPmJgYMjMz2bFjByUlJcc8r4B/1x4ul4va2tpjnlfk2kOuPZpfe6xfv576+np69+7N4MGDQ+Lao6qqisjISCZOnEhOTg6VlZWAuoChJ99y7SHXHnLt0c61x623Np0jXC7GXHUVcT/9xAf3z2dfpIkrh46jqKiox117nHvuuRQWFpKTk0NpaSnXXXcdv/rVr4Je56/b4Zkx4I034NVXQcOpUwRBCC3mjJ3Dz/t+5t/b/82CaQu6Ohyhp6EEgcPhCOblXUJ1dbUCKNXV1YqtzqbwMAoPo9jqbJq/1+rVq8UpTt9wuRRl1ChFUe9xURRby/ZomDhbcejQIWXEiBEKoJjNZuXJJ5/UILKWGLXs4hRnZzibf2b1ZHr37q1s27ZNURRFeeGFF5STTjpJURRFWbp0qTJs2LCuDM0n2qvHUGmPennFKU5xilOcxnT29GuP008/XVm+fHlXhxE0Wtfj1muuafpf9ZNPgnJVVVUpVVVVmsSlpUsP3+LFizVzSd4Cw8hl1To2RdEud8eKbefhnQoPo4Q/Gq5U1FYE7dMytkDpjLx1tc/IefPnM8ukKP6NDXS73TzxxBO8/PLLlJaWsmPHDoYPH84DDzxAamoqN954o+adLVrimSuyuroas9VM7FPqvGW2+2zEWGKO82r/cLvdmi7yIs5u6FQUsNshMxOO3mVFRoa62HezdTK6PM5jsG/fPmbOnMljjz3G3LlzDRunOMUZis7mn1nN5zfuacTGxrJ582ZSU1O58MILmTFjBr///e8pLi5mzJgxOByOrg7xmLRXj6HSHvXyilOc4hSnOI3plGuP7oHW9Zh/7bWkvfee+uT55+GuuwJ2OZ1OQJtFk7V06eFbsmQJs2fP1sQleQsMI5dV69hAu9wdL7YJ/5jA5kObeffid7lm0jVB+7SMLRA6K29d6TNy3vz5zPL7Cujxxx/n7bff5plnnvEuzgHqFAWvv/66/9F2YzxDwMUpznZRFDj5ZOjVq6kTY9QoWLu2zWLfRi774MGD2bhxI/PmzTN0nOIUZ092hjrjx4/n5ZdfZuXKlSxbtoxzzz0XgAMHDtCnT58uji4wQqnthEqs4hSnOMUpTuM4Q4V3332Xd99917vQqOf58R49jub/n7b6X9VfHA6HZjehaOnSw6clkrfAMHJZQzlvc8bOAeDzbZ9r4tMytq5E2pv++L1Gxrvvvsurr77KWWedxa9//Wvv9kmTJnnnjxVU6urqxCnOjqmthZ9+anqekaF2YrRzh5VRyu52u/n73//Or371qxa9uBEREQE7j4c4xSlO4emnn2bOnDk8++yzzJ8/n0mT1BWFFi9ezLRp07o4usAIpbYTKrGKU5ziFKc4jeMMFa677jpMJhOXX345FouF66677rivMZlMXHvttfoH102JidFuJgwtXXr4tETyFhhGLmso523O2Dk89uNjfL3ra+z19uPOcCN563qfkfPmD353ZOzfv5+RI0e22e52u2loaNAkqO5C7969xSnOjmk+q1tpKfTr1+HdLUYou9vt5qabbuKtt97iq6++4t///nebIWlGiFOc4hRn9+P000+nvLycmpoaEhISvNt/9atfER0d3YWRBU4otZ1QiVWc4hSnOMVpHGeoUFhYCOCdbcLzvCOOHDlCTU2N7nEZmiBHZNjtdoAWM3wYwaWHT0skb4Fh5LKGct4y+mcwrPcwCqsK+c+u/zBv3LygfFrG1pVIe9Mfvzsyxo0bx8qVKxk6dGiL7Z9++imTJ0/WLLDuwJAhQ8QpzvZRFDjllKbnMTHHvCDs6rI378QAWL58OatXr+b0008P2Okr4hSnOAUAs9lMY2Mjq1atAmDMmDGkpqZ2bVBBEEptJ1RiFac4xSlOcRrHGSq0/l6j9fPWPPHEEzz00EM0NjbqGZbhUDScWsrIdxgb+Y5lyVtgGLmsoZw3k8nEpeMu5ZmfnuHTrZ8etyND8tb1PiPnzR/8XiPjwQcf5LbbbuPpp5/G7Xbz2WefcfPNN/PEE0/w4IMP6hFjyLJp0yZxirN9amth/Xr194wMOM4dxV1Z9tadGGazmUWLFrXpxPDH6Q/iFKc4Bbvdzg033MCAAQM49dRTOfXUUxk4cCA33ngjtbW1XR1eQIRS2wmVWMUpTnGKU5zGcXZnlOYj6wW/sdvt3juDjeTSw6clkrfAMHJZQz1vns6LL3d8iaPh2GsvSN663mfkvPmD3x0ZF110EUuWLGH58uXExMTw4IMPkp+fz5IlS5g5c6YeMQpC92blyqDvatGLjjox5s07dm+7IAiCltx9992sWLGCJUuWUFVVRVVVFV988QUrVqzgt7/9bVeHJwiCIAiC0HMI8n9Xq9XaZopiI7j08GmJ5C0wjFzWUM9b1sAsUuJTsDfY+XrX10H7tIytq5D2pj9+d2QAnHLKKSxbtoxDhw5RW1vLqlWrOOecc7SOLeQZNmyYOMV5fHy4EOyKOAPpxDBEPsUpTnF2O/71r3/xxhtvcN555xEXF0dcXBznn38+r732Gp9++mlXhxcQodR2QiVWcYpTnOIUp3GcQjcmyI6MhoYGzdZX1dKlh09LJG+BYeSyhnreTCYT89LU74c+zT/2/2SSt673GTlv/uB3R8bw4cM5fPhwm+1VVVUMHz5ck6C6C/X19eIUZ0g6Ax2J0R3KLk5xdkdnqFNbW0tycnKb7UlJSSE7tVQotZ1QiVWc4hSnOMVpHKcgdERYWBhhYQHdU6urSw+flkjeAsPIZe0Oebt0/KUALNm+BGejM2iflrF1BdLe9MfvEuzZsweXy9Vme11dHfv379ckqO6CHvkQZzdx+jmvamfH+Ze//CWg6aS6VR2JU5zdyBnqnHjiiTz00EM4nU0Xxw6Hg0ceeYQTTzyxCyMLnFBqO6ESqzjFKU5xitM4zlAiLy/P58eBAwe6OtyuQcPFvk0mEyaNplbW0qWHT0skb4Fh5LJ2h7xNGzSNwXGDOVJ/hG8Kvgnap2VsXYG0N/0J93XHxYsXe39funQp8fHx3ucul4tvv/2W1NRUTYMThG6JosApp3R1FMfk17/+NV9++SUrV66UNTEEQehy/vrXvzJr1iwGDx7MpEmTANiwYQNWq5WlS5d2cXSCIAiCIIQyWVlZPn+5oyhKt/giqCvRetoVLTHytCuSt8Awclm7Q97CTGFcknYJL2S/wKdbP+XCMRcG5dMytq5A2pv+mBTFt1vDPcNPTCYTrV8SERFBamoqzz33HBdccIH2UWpITU0N8fHxVFdXY7aaiX0qFgDbfTZiLDGavldDQwMRERHiFGdL7HaIVdsdGRmQl3fcu1q6Ik673c7q1as566yzNHMGgjjF2ZOdzT+z4uLiNH2fUKO2tpYPP/yQ/Px8ANLS0rjqqquIiorq4siOT3v1GCrtUS+vOMUpTnGK05jOnnjt8c477/j9mvnz5+sQiXZoXY9br7+ecW+/rT5ZuBBuvTVgl2eErRaLzmrp0sO3ZMkSZs+erYlL8hYYRi6r1rGBdrnzJ7ZVxas45a1TiI+Mp/SeUiLDI4PyaRmbr3RF3jrbZ+S8+fOZ5fPUUm63G7fbTUpKCocOHfI+d7vd1NXVsX37dsN3YnQ2ni9bxCnODlm50qehuXrH6Xa7qaioaPH3mJgYvzoxWju1QpziFGfPZvXq1dx///089NBDDBo0iOeee47nnnuOm266KSQ6MToilNpOqMQqTnGKU5ziNI4zlJg/f77fj56GouHUUg6HA4fDEWRE2rv08GmJ5C0wjFzW7pK3k4acxIDYAVTXVbN89/KgfVrG1tlIe9Mfv9fIKCwspG/fvnrE0u3Qo4GIs5s5fbwI1DNOz8LeJ598MiUlJZo4tUSc4hRnz+XTTz9lxowZvPDCC7z++utccMEF/PnPf+7qsDQhlNpOqMQqTnGKU5ziNI5TEDoiJiaGmBhtZsPQ0qWHT0skb4Fh5LJ2l7x5ppcC+DT/06B9WsbW2Uh70x+f18hojt1uZ8WKFRQXF1NfX9/ib3fccYcmgXUHevXqJU5xGtrp6cTwLOx9zjnnkJeXR3h4QKeGkCq7OMXZk5yhylNPPcXNN9/MwoULMZvNPPXUUzz55JPcc889XR1a0IRS2wmVWMUpTnGKU5zGcQrdmCBHZNjtdgAsFkvQoWjp0sOnJZK3wDByWbtT3uaNm8ffc/7Ov7f9m1cueAWLueXrJG9d7zNy3vzB728r161bx/nnn09tbS12u53ExETKy8uJjo4mKSlJOjKaMWzYMHGK07DOoUOHtujEMJvNPPjggwF3YkDolF2c4uxpzlBl+/btfPzxx5jNZgB++9vf8uCDD3Lo0CGSkpK6OLrgCKW2EyqxilOc4hSnOI3jFLoxQXZkaH23spYY+W5lyVtgGLms3SlvJ6ecTHJMMqX2Ur4v/J5ZI2cF5dMyts5E2pv++D211F133cXs2bOprKwkKiqK1atXU1RUxJQpU7rNdA9asXHjRnGKswlFURf6PtoLqokzQNxuN5dffnmLToxFixYxb968oLwhX0fiFGc3dYYqtbW1LRb7slgsWK1WbDZbF0alDaHUdkIlVnGKU5ziFKdxnILQEXa73XtnsJFcevi0RPIWGEYua3fKmznMzNy0uQB8svWToH1axtaZSHvTH79vvV6/fj2vvPIKYWFhmM1m6urqGD58OM888wzz589n7ty5esQpCKGNosDJJ8NPP3V1JN7ppL788ktAu04MQRAEPXj99deJjY31Pm9sbOTtt99usV6XjAYVBEEQBEHoJIIckWG1WjUKRFuXHj4tkbwFhpHL2t3yNm/cPP6R+w8+3/Y5//jFP4gwRwTl0zK2zkLam/743ZERERFBWJg6kCMpKYni4mLS0tKIj49n7969mgcYygwdOlSc4lSx29t2YsyYAdHRgTsDoPWaGFp3YoR0HYlTnN3YGaqkpKTw2muvtdjWv39/3nvvPe9zk8kUkh0ZodR2QiVWcYpTnOIUp3GcQjcjyM6L5jQ0NAAQFRVlKJcePi2RvAWGkcva3fJ26tBT6Rvdl/Lacn7Y8wMzR8wMyqdlbJ2FtDf98bsjY/LkyeTk5DBq1ChOO+00HnzwQcrLy3nvvfdIT0/XI0ZNWLhwIQsXLsTlcgGQm5tLWGTTzFo5OTkkJSQxbNgw79DaoUOH4na7vR00GRkZ7Nq1C5vNRkxMDKNHj2bdunUADB48GLPZTFFREQATJ06kuLiYoqIirFYr48ePZ+3atQAMHDgQq9XK7t27AUhPT2ffvn1UVVVhsVjIyMhgzZo1gPqFTWxsLLt27QKgb9++7Ny5k4qKCsLDw5kyZQpr1qxBURT69etHQkICO3bsAGDMmDFUVFRQVlZGWFgYU6dOJTc3F5fLRZ8+fUhKSiI/Px+n04nFYqGmpobS0lIApk+fTl5eHg0NDSQkJDBw4EC2bNkCwIgRI6itreXgwYMAZGVlsXnzZpxOJ/Hx8aSkpLB9+3aKiopITU2lsbGRffv2AZCZmcm2bduora0lNjaWESNGsGHDBkD9wgqguLgYgEmTJlFQUIDNZiM6Opr4+Hiys7O9+Q4PD2fPnj0ATJgwgeLiYqqrq7FaraSnp5ObmwvAgAEDiI6OpqCgAIDx48dz4MABKisraWxspH///l5vcnIycXFx7Ny5E4C0tDQOHTrE4cOHMZvNZGVlkZOTg9vtpl+/fiQmJrJ9+3YARo8eTWVlJXv37qW4uJhp06axdu1aGhsamHTDDXj6Ptd+9RWp48djc7spOVrP06ZNY/369dTX19O7d28GDx7M5s2bARg+fDiHDh3ytq0pU6awZcsWnE4ncXFxpKamtmizLpfLm+/JkyezY8cO7HY70dHR/PnPf+bdd98F1E6Ml19+mSFDhpCdnc3EiRMpLCzkyJEjREVFkZaWRl5eHgCDBg3CYrFQWFjozffevXupqqoiMjKSiRMnkpOTg9PppK6ujpiYGG++x40bR0lJCRUVFURERJCZmenNd1JSEvHx8d58jx07lvLycsrLy71tdseOHRQVFdG3b1/69u3Ltm3bABg1ahTV1dUcOnSoTZtNTEykf//+bN261dtm7XY7JSUl3vKsX7+euro6evfuzZAhQ9i0aROgzhFcX1/P/v37vW02Pz8fh8NBr169OjxHOJ1OEhIS/DpH7Nmzh5qamg7PEZ7jyJ9zRFpaGqWlpR2eIxobG70x+HqO8OS7o3OE2WwmNjbWr3OEJ98dnSMqKio4fPiwX+eIsWPHettse+eIvXv3es/Jvp4jWrfZ1ueIPn36sGvXLr/OEWVlZZhMpqZzRGMjiYmJJCcne8/JERER2Gw2b0w9FU/9hSrtXXvExMSQmZlJYWEhRUVFxzyvgH/XHp42dKzzilx79JBrj1bnFYCRI0dis9m8n4Wdce0RGxvLyJEjWb9+PdA0N2/zz0K59pBrD7n2kGsPIcQIslPDpGGniJYuPXxaInkLDCOXtbvlLTwsnEvSLuGVta/w8ZaPW3RkSN663mfkvPmF4ic5OTnKd999pyiKopSWliqzZs1SevXqpWRmZirr1q3zV9fpVFdXK4BSXV2t2OpsCg+j8DCKrc6m+XutXr1anD3d6XYrSmmpoqiTSylKRoa6LRhngLhcLuXmm29WAMVsNitPPvlk0M7WhGQdiVOcBnY2/8wSQpf26jFU2qNeXnGKU5ziFKcxnXLt0T3Quh4333BD0/+0r70WlMtutyt2u12TuLR06eFbvHixZi7JW2AYuaxax6Yo2uUu0Ni+L/xe4WGU3v/bW6lrrAvap2Vsx6Kr89YZPiPnzZ/PLL9HZGRlZXl/T0pK4uuvv9amR0UQuhtuN0yZAkfvQgRg5UpNh+X6Q1hYGC+//DLh4eGceeaZDBkypEviEARB8IVFixZx+eWX+7Sv5270GTNm6ByVIAiCIAhCD0TD/2Hr6+sBiPZxmuXOcunh0xLJW2AYuazdMW+npJzCgNgBHLQd5JuCb7hg9AVB+bSMrTOQ9qY/JkVRFC1EeXl5PPjgg94FhI1KTU0N8fHxVFdXY7aaiX1KXUDUdp+NGEuMpu9VV1dHZGSkOHui02KBzMyWnRgzZgTckRFSZRenOMWpmbP5Z1ZcXJym72N0TjvtNA4dOsT111/P7NmzSUtLa/H36upq/vvf//L++++zbNky3njjDS688MIuivbYtFePodIe9fKKU5ziFKc4jensydce3QlPPZaUlBAVFYXJZMJsNlNfX09UVBS1tbXExMR4pyB2OBxYLBZcLheKohAREYHT6fTus/+ee0h/800Aal98EeWGG1AUBbfb3WZfz8+oqCjq6uowm80AuFwuIiMjqampISoqisbGRu++VquVhoYGwsLCMJlMNDQ0YLVacTgcbbyefU0mEy6Xi/r6euLj4/0uU/M4PdOr1dXV4Xa7iYmJ8atMHcW5bNkyzjzzTL/K1FE9hYeH43A4iI2N9atM7dVTVVWVtw78LVN79XSsOg2k7S1btoxzzz3XrzJ1VE/19fW4XC569erlV5k62tdut2MymYiKigr4ePL8NJvN1NXVER0dHfDx1DrOr7/+mpkzZwZ0PDWvp+rqam+d+ns8/c/S/+GV9a9wWdplvHruq0RERHinEW3eRgJtew0NDTQ2Nh63Tv1pe99//z0zZ84M6Hhqvm9YWJj3/QI9nprv6znue/XqFfDx1NFxH8jx1LpMK1eu5JRTTgn6XG632xkwYIBP1x5hx/xrK5YuXco999zDH//4R+8cy9u2bePiiy9m6tSpuN1uf3TdHs+8seLsAU5FURf0ttsp2LgRysqaOjFGjYIjR4IajRFInG63m7vvvts7x68WzuMhTnGK05jOUGTFihU8/fTTLFu2jPT0dOLi4hg1ahQTJkxg8ODB9OnThxtuuIGUlBQ2b95s2E6MjgilthMqsYpTnOIUpziN4xS6hoULFzJu3DimTp3a1aF0iNPpxOFwaOJyOBw4nU5NXHr4tETL2LSsAz18WuJ0OjWtUy19Rm5vwdTp3NFzAfi/Xf9HbUNt0L7WGDlvRj4nGfk49Qefp5Z64403uPnmm0lMTKSyspLXX3+d559/nttvv53LLruMzZs3t7lbsqdjs9nE2Z2digK1terPU07xdlyMa71fXh7Exgb+Pvgfp9vt5qabbuKtt97inXfe4bvvvmPSpElBOX1BnOIUpzGdocqFF17IhRdeSHl5OatWraKoqAiHw0Hfvn2ZPHkykydPJizMr3syDEMotZ1QiVWc4hSnOMVpHKfQNSxYsIAFCxZ4R2RERUW1uLvVM6WIZwSOxWJp8bw5njuKLRYL+5vdkBcdEwMxMR3u2/yn1Wpt4+3fv3+7+3oczfG8vqN9m5fD3zK1F2dERIR3uz9l6ihOk8lEbKvvAo5XJmi/njzTwnj297VM7e3bug78KVN79eRLnfrT9kwmExaLxa8ydbRv8+3+lKmjfZOSkrzPAz2ePD+1qNPWcXpGiwRyPEFTPbWuU3+Op5ljZzI0fihF1UWsKl3FvHHzOmwjgbQ9f+vUl3pqnbdA215HdRpo22vuC/R48ue497ftmUwmEhIS/CpTe/v6M1mUzx0ZL7zwAk8//TT33nsv//rXv7j00kt56aWX2LRpE4MHD/b5DXsSMTHaTlUlTgM5FQVOPhl++unY+82Y0eYiLxD8ibN5Jwao068UFBS06cgwVD7FKU5x6uoMdfr27cvFF1/c1WFoSii1nVCJVZziFKc4xWkcp9C9aDGvQJDrZdjtdqDtF31d7dLDpyWSt8Awclm7a95MJhOXjb+MZ356ho+3fMy8cfMkbwbwGTlv/uBzR0ZBQQGXXnopAHPnziU8PJxnn31WOjGOwejRo8XZXZ21tW07MTIyYOVK6hsamk4M0dGaLIzma5ytOzHMZjOLFi1i7ty5ATv9QZziFKcxnYLxCKW2EyqxilOc4hSnOI3jFLoZ2iytCmi70KzWi9YaeRFcyVtgGLms3Tlvl6dfzjM/PcOXO77kSN0RyZsBfEbOmz/4PB+Dw+HwFtpkMhEZGcmAAQN0C6w7sG7dOnH2BGdpKdhs3imk1u3YoY7CiInRpBMDfIuzo06MefPmBez0F3GKU5zGdArGI5TaTqjEKk5xilOc4jSOU+hmNO/ICPJ/XIfDoelc+VrO+a61T0skb4Fh5LJ257xl9M9gdJ/ROBudLN6+WPJmAJ+R8+YPPo/IAHj99de98/s1Njby9ttv07dv3xb73HHHHdpFJwhGw7MuxtEhWUBTp0UX4m8nhiAIgiAIgiAIgiD4TZAdGVpOa6L1FClGnnJF8hYYRi5rd86byWTi8vGX8+iPj7JoyyLmjJyjUWTdO296+oycN3/wuSMjJSWF1157zfu8f//+vPfeey32MZlM0pHRDD2m3RJnFzp9XBejs+MMtBOjy/MpTnGKs9OcgvEIpbYTKrGKU5ziFKc4jeMUuhcmDaeWcrlchnTp4dMSyVtgGLms3T1vl6VfxqM/PsrSXUsps5WRGJWoQWTdP296+YycN3/wuSNjz549OobRPTGbzeLsTs721sWYMUNdByNQp48cy/ntt98GNBKjy/MpTnGKs9OcgvEIpbYTKrGKU5ziFKc4jeMUuhkaTi2laNgpoqVLD5+WSN4Cw8hl7e55G9dvHBOTJ7KxdCNLdi3h2vRrNYis++dNL5+R8+YPPq+RIfhPUVGROLuLU1FaTiflWRdj5co2F3KdHefMmTN54YUXCA8P92s6qW5XR+IUpzi7LS6XizfeeIMrr7ySs88+mzPPPLPFIxQJpbYTKrGKU5ziFKc4jeMUhI6IiIggIiLCcC49fFoieQsMI5e1J+Tt8vGXA/D5js8lb13sM3Le/EE6MgShIzydFzYbZGZCcnLT3zRezDtY7rjjDrZt2yZrYgiC0C258847ufPOO3G5XKSnpzNp0qQWD0EQBEEQBEE/TBqOyHA6nTidziAj0t6lh09LJG+BYeSy9oS8XZZ+GQA/FP9AcUVx0D7oGXnTw2fkvPmDX4t9C/4xceJEcYaq81jrYbQznZRPziBo7nS73axbt44pU6a02GfEiBEBO7VCnOIUpzGdoc6iRYv45z//yfnnn9/VoWhGKLWdUIlVnOIUpzjFaRyn0M3QsCMjJiYmyGD0cenh0xLJW2AYuaw9IW/DE4YzbdA01uxfw9fFXzNm0JignT0hb3r4jJw3f5ARGTqix7oi4uwkZ3vrYWRkwJEj7U4n5ZMzCDxOz8LeJ5xwAl988YUmTi0RpzjFaUxnqGOxWBg5cmRXh6EpodR2QiVWcYpTnOIUp3GcQjdDw7nV7XY79ubTNhvEpYdPSyRvgWHksvaUvF02Xh2V8fHmjzXx9ZS8ae0zct78QToydKSmpkacoepsfqHmWQ8jLw9iY497B4pecXo6Md566y0aGxu54oorKC0tDcqpNeIUpziN6Qx1fvvb3/LCCy90mwXKILTaTqjEKk5xilOc4jSOU+hetPgPWIMRGVrdGaylSw+flkjeAsPIZe0pefvl+F8C8POBn9lbvTdoX0/Jm9Y+I+fNHwLqyCgoKOBPf/oTV1xxBYcOHQLgP//5D1u2bAkoiIULF5KamorVamX69OmsWbPGp9ctWrQIk8nExRdfHND76o3VahVnKDoVBU45pem5n+th6BGnxWLxdmIAmM1m3n33XZKbr9vhJyFdR+IUpzh7FKtWreKDDz5gxIgRzJ49m7lz57Z4BEJXX3uEUtsJlVjFKU5xilOcxnEK3QwZkdHlSN4Cw8hl7Sl5Gxw3mJMGngTAR5s/CtrXU/Kmtc/IefMHvzsyVqxYwYQJE8jOzuazzz7DZrMBsGHDBh566CG/A/j444+5++67eeihh8jLy2PSpEnMmjXL20HSEXv27OGee+7hlOZfOBuM8ePHizMUnXY7rF+v/p6Rccz1MHx2BoHb7eaFF15o0YmxaNGioBf2Duk6Eqc4xdmj6N27N3PmzOG0006jb9++xMfHt3j4ixGuPUKp7YRKrOIUpzjFKU7jOIVuRvOOjOuug1WrAlZFRUURFRUVfEwau/TwaYnkLTCMXNaelLerJlwFwAebPgja1ZPy1lPamz/43ZHxhz/8gccff5xly5ZhsVi8288880xWr17tdwDPP/88N998M9dffz3jxo3j5ZdfJjo6mjfffLPD17hcLq666ioeeeQRhg8f7vd7dhZr164VZ6g5W4/GOM56GD45g8AzndQ777wDaNeJASFcR+IUpzh7HG+99dYxH/5ihGuPUGo7oRKrOMUpTnGK0zhOoRvT2Njyf2Y/cTqdOJ1OTULR0qWHT0skb4Fh5LL2pLydn3o+FrOFjaUb2Vi6MShXT8pbT2lv/uB3R8amTZuYM2dOm+1JSUmUl5f75aqvr2ft2rWcffbZTQGFhXH22Wfz888/d/i6Rx99lKSkJG688cbjvkddXR01NTUtHoLQAkVRR2HY7VBW1nI0RhfOH9d8TQzQthNDEAQhFCkrK2PVqlWsWrWKsrKygBxy7SEIgiAIguAfJg2nloqIiCAiIsJwLj18WiJ5Cwwjl7Un5a1fr37MGj4LgA82Bjcqoyflrae0N38I9/cFvXv35uDBgwwbNqzF9nXr1jFo0CC/XOXl5bhcrjbz/CcnJ7Nt27Z2X7Nq1SreeOMN1nu+bD4OTz31FI888kib7bm5uYRFNvXj5OTkkJSQxLBhw9i4Ue0dHDp0KG63m7171cVoMjIy2LVrFzabjZiYGEaPHs26desAGDx4MGazmaKiIgAmTpwIQHZ2NlarlfHjx3vvdBk4cCBWq5Xdu3cDkJ6ezr59+6iqqsJisZCRkeGdq7t///7Exsaya9cuABISEti5cycVFRWEh4czZcoU1qxZg6Io9OvXj4SEBHbs2AHAmDFjqKiooKysjLCwMKZOnUpubi4ul4s+ffqQlJREfn4+DoeDiooKampqvItHT58+nby8PBoaGkhISGDgwIHeNVBGjBhBbW0tBw8eBCArK4vNmzfjdDqJj48nJSUFh8NBdnY2qampNDY2sm/fPgAyMzPZtm0btbW1xMbGMmLECDZs2ABASkoKAMXFxQBMmjSJgoICbDYb0dHRJCcnk52d7c13eHg4e/bsAWDChAkUFxdTXV2N1WolPT2d3NxcAAYMGEB0dDQFBQWAOnT6wIEDVFZWUl9XByefDD/91KaN5Dz/PGOOHOHQoUMcPnwYs9lMVlYWOTk5uN1u+vXrR2JiItu3bwdg9OjRVFZW4nA4WLNmDdOmTWPt2rU0NjaSmJhIcnIy+fn5AIwcORKbzUZJSQkA06ZNY/369dTX19O7d28GDx7Mtddey2effQaonRiPPfYYQ4YMobHx/9k797imq/+Pv7Zx2YW73FRAFATBGyJiXrqYmpcy7aampZla9tW0zEq7eMnS+qpf81emfb95z9LKNC2zLNPMCwgIKqKC4h0Q5OYGg7Gd3x+4jxtsuI3P3Gfwfj4ee+i2z557n/fn7Oyw8znn1CAzMxNqtRpeXl4IDw83qrNarZbLd7du3XDu3DmoVCp4eHggMjKS++zIZDLk5+cb1dnc3FzcunULMpkMMTExSEtLAwC0bt0abm5uyM3N5fJ95coVlJaWwt3dHV26dMGxY8dQWVmJS5cuQaFQcPmOjY1Ffn4+iouL4erqivj4eO48BgYGwtvbG9nZ2QCADh06oKioCEVFRVydVavVSEpKgr+/P/z9/bm2oX379igrK+OWgjGss35+fggODsbp06e5OqtSqbh8t2zZEunp6aiqqoKPjw9CQ0Nx8uRJAEDbtm1RXV2Na9eucXVW/znx9PQ020ZUVlaiqqrKqjbi4sWLKC8vN9tG6D9H1rQRMTExKCgoMNtGeHt7c/m3tI3Q59tcGyEWi6FUKq1qI/T5NtdGVFZWIjMz06o2okOHDlydNdVGAHfaZEvbiLp1NigoCF5eXlyd9fX1RU5OjlVtRGFhIUQikdk2orKyEjdv3oRSqeRiau6oVCq8+uqr2LhxI3Q6HYDadnHcuHH47LPPILdiCUBH9z0UCgXi4+Oh1WqRlJTUYLsCWNf38Pf3R1ZWVoPtCvU9BND3qK4GALPtSkxMjMP6HqdOnQIAtGvXDu7u7lyM3bt3p74HqO9BfQ/qexDNGB4HMphAXfbw8QnlzTaEXNbmlrdRMaOwK3sXvjn1DRYPWAyxyKZtm5td3oTocijMSt544w3Wt29flpeXxzw9PVl2djb7559/WLt27dj8+fOtcl27do0BYIcPHzZ6/M0332SJiYn1ji8vL2fh4eFs9+7d3GPjx49nw4cPN/searWalZWVcbcrV64wAKysrIwpq5QM88EwH0xZpbQqdku4ceMGOYXuvHCBsdpumfGtTx/GdDrbnDzF+euvvzJ3d3cmkUjYmjVreHEa4jTniJzkbMbOsrIy7jurOfPSSy+xdu3asd27d3Pf57/88guLiIhgU6ZMscrl6L6HHmepj/bykpOc5CQnOYXppL5H04Dv83hm9Oj6fzM3Ija+4uLTZQ/fzp07eXNR3mxDyGXlOzbG+MudPfJWcLOA+XzswzAf7K/cvwQTG2PCzltzqW+WfmdZPfy1aNEidOjQAaGhoVAqlYiNjcUDDzyA3r1747333rPK5e/vD4lEwl1lo6egoADBwcH1jj9//jwuXryIYcOGwcXFBS4uLti4cSN27twJFxcXk1ePuLu7w8vLy+h2r9Bf9UhOgTn1S0kplfB48ME7jxcUAEpl7c2GvTH4jnPw4MHYsWMHtmzZYpcN+AR9jshJTnISBmzbtg1r1qzBkCFDuO/yoUOH4n//+x9++OEHq1xC6Xs4U91xlljJSU5ykpOcwnESTQtaWsrxUN5sQ8hlbW5585R54umY2qXSvz7xdaNczSlvzaG+WYPVAxlubm743//+h/Pnz+Pnn3/G119/jTNnzmDTpk2QSCRWu7p3744///yTe0yn0+HPP/9Er1696h3foUMHnDx5Eunp6dzt8ccfR79+/ZCeno7Q0FBri0M0NxirXUrKwwPw9ITs9tIdiIsDAgJq98RQKGwexGhcaPU7h4MHD6Y9MQiCaPZUVFTUWwoKqF0ipqKiwioX9T0IgiAIgiCshMeBDCFvXivkzXApb7Yh5LI2x7w91+U5AMD3p7+HusY2f3PMm9BcjsTqPTL++ecf9O3bF2FhYdyaoY1h5syZGD9+PBISEpCYmIhPP/0UKpUKEyZMAACMGzcOrVu3xuLFi7m1RQ3x8fEBgHqPCwF7xETORlJRUX8/jLg4IDWVt8ELW+LU6XSYPHky2rdvj9mzZ/PivBvkJCc5m4/T2enVqxfmzZuHjRs3QiqVAgAqKyuxYMECk4MPd0MIfQ9nqjvOEis5yUlOcpJTOE6CMIdCoRCkyx4+PqG82YaQy9oc83a/z/0I9QrFlfIr+OXcL3gq9imHx8YnVN/sj9UzMh5++GG0bdsW77zzDreZXWMYNWoUli5dirlz5yIuLg7p6enYs2cPd+Xl5cuXuU3bnA39BnLkFKizoADn0tKAtDRAbNsmQ6awNk6dTodJkyZh7dq1mDNnDv7973832mkJ5CQnOZuP09lZsWIFDh06hJCQEPTv3x/9+/dHaGgoDh8+jBUrVljtE0Lfw5nqjrPESk5ykpOc5BSOk2ha8Lm0lEqlgkqlEpzLHj4+obzZhpDL2hzzJhaJMabzGADA1ydtW16qOeZNaC5HYvWMjOvXr2PLli349ttv8fHHH6NLly4YO3Ysnn32WYSEhNgUxLRp0zBt2jSTz+3fv7/B165fv96m97wXlJaWklPIToUCJdXVvC8jZU2c+kGMdevWAQAkEgnatWvXKKelkJOc5Gw+TmenU6dOyM7OxubNm3HmzBkAwLPPPouxY8dCJpPZ5HR038OZ6o6zxEpOcpKTnOQUjpO4w99//40lS5YgNTUVeXl52L59O0aMGGHRaw8dOoQHH3wQnTp1Qnp6ul3jbBAeBzKEfIWxkK9YprzZhpDL2lzz9lyX5/DJoU/wy7lfUFxZDD+Zn0Nj4xOqb/bH6svQ/f39MW3aNBw6dAjnz5/HM888gw0bNiA8PBwPP/ywPWJ0Wtzc3MhJTrOYGsTYsmWLyT0xmlrZyUlOct5bZ1NALpdj8uTJWLZsGZYtW4ZJkybZPIghBJyp7jhLrOQkJznJSU7hOIk7qFQqdO3aFStXrrTqdaWlpRg3bhz69+9vp8isgGZkOBzKm20IuazNNW+dAjuha1BXaHQafJ/5vcNj4xOqb/ZHxEztMGwFWq0Wv/76K95//32cOHECWq2Wr9jsQnl5Oby9vVFWVgaJVAKPxR4AAOUcJRRu/I5OMcYg4vlqf3I20qlS1W70DQBKJZhc7pA4rRnEsNRpjzjJSU5yOtZp+J3l5eXF6/sInZ07d2LIkCFwdXXFzp07Gzz28ccfv0dR2Yap8+gs9dFeXnKSk5zkJKcwnc2573EvEIlEFs/IGD16NNq3bw+JRIIdO3ZYNSOD7/OY/fTTaL9tm/GDNv6UpN9sVr/vWWPg02UP365duzBs2DBeXJQ32xByWfmODeAvd/bO25JDS/DWH2/h/rD78feEvx0aG+A8eROKSw9febPmO8vmjQEOHTqEf/3rX2jZsiXGjBmDTp064ZdffrFV1yRJTk4mJznrYe0ghiVOWyAnOcnZfJzOyIgRI1BSUsL939ztiSeecHCktuFMdcdZYiUnOclJTnIKx0k0jnXr1uHChQuYN2+eRcdXVVWhvLzc6MYnfO6RUVVVhaqqKsG57OHjE8qbbQi5rM05b892fhYiiHDw8kFcLL3o0Nj4hOqb/bF6j4w5c+Zgy5YtuH79OgYOHIgVK1Zg+PDhkMvl9oiPIPiFxw6YLdgyiEEQBNEc0el0Jv9PEARBEATRlMnOzsbs2bNx8OBBuLhY9pPN4sWLsWDBgnqP//rrr7z8VtPBRF9s165djfY2dXQ6HeXJBihvtuNMuevs2Rknbp3A+9+/j5HBIx0aizPlTUjwlbeKigqLj7V6IOPvv//Gm2++iZEjR8Lf39/alzcrgoODySkkJ2PA/ffz6zRBQ85r165h9+7dAKwbxBBkPslJTnI6jbMpUlpaCh8fH0eHYTPOVHecJVZykpOc5CSncJyEbWi1WowZMwYLFixAVFSUxa+bM2cOZs6cyd0vLy9HaGgohgwZwsvSUufXrq33mK3LiSiVSgCAh37J50bAp8sePj6XSKK82YaQy8p3bAB/ubsXeSs6XoQXd76I1OpUbHxso8XLJjb3vAnBpYfPpaUsxeqlpfRLStEgxt3hs3KQkwdnRQWgX1c0Lg6Qy+95nKGhodi3bx9at25t1UwMQeaTnOQkp9M4nZ1PPvkEW7du5e4/88wz8PPzQ+vWrZGRkeHAyGzHmeqOs8RKTnKSk5zkFI6TsI1bt24hJSUF06ZNg4uLC1xcXPDBBx8gIyMDLi4u2Ldvn8nXubu7w8vLy+gmVLRaLW97q/LpsoePTyhvtiHksjb3vD0Z8ySkLlJkFWUhNS/VYbHxCdU3+2PRQMbOnTuh0Wi4/zd0I+6Qk5NDTiE5DZeVOngQEIkcEmdsbCyys7OtWk5KkPkkJznJ6TROZ2f16tUIDQ0FAOzduxd//PEH9uzZgyFDhuDNN990cHS24Ux1x1liJSc5yUlOcgrHSdiGl5cXTp48ifT0dO42ZcoUREdHIz09HT179nRMYDwu0ezu7g53d3fBuezh4xPKm20IuazNPW/eUm+M6DACALAhfYPDYuMTqm/2x6KlpUaMGIH8/HwEBgZixIgRZo8TiURNYnSHaILUXVbKwilrjUWn02H9+vUYP348JBIJ97hMJrsn708QBNEUyM/P5wYyfv75Z4wcORKPPPIIwsPDHfcHPUEQBEEQhAUolUqjwaLc3Fykp6fDz88PYWFhmDNnDq5du4aNGzdCLBajU6dORq8PDAyEVCqt9/i9hM/NvisrKwEAUqlUUC57+PiE8mYbQi4r5Q14oesL2HJqC7459Q2WPrIU7i53/6Gd8uZ4lyOxaEaGTqdDYGAg939zNxrEMCYmJoacQnGqVPWWlWq00wx6p35j74kTJ+KFF15o1OdDcPkkJznJ6VROZ8fX1xdXrlwBAOzZswcDBgwAADDGnLbv4Ux1x1liJSc5yUlOcgrHSdwhJSUF3bp1Q7du3QAAM2fORLdu3TB37lwAQF5eHi5fvuzIEO8pCoUCCoVCcC57+PiE8mYbQi4r5Q0Y0G4AWnm2QnFlMX7J/sUhsfEJ1Tf7Y/UeGRs3bkRVVVW9x6urq7Fx40ZegmoqFBQUkFMITp0OiI+/c//2slKNcjZAQUEBN4ixbt06AMC3336LY8eONcrJN+QkJzmbj9PZefLJJzFmzBgMHDgQN2/exJAhQwAAx48fR2RkpIOjsw1nqjvOEis5yUlOcpJTOE7iDg899BAYY/Vu69evBwCsX78e+/fvN/v6+fPnI11/UZ6j4HFGhkqlgkqlEpzLHj4+obzZhpDLSnkDJGIJnu/yPABgffp6h8TGJ1Tf7I/VAxkTJkxAWVlZvcdv3bqFCRMm8BJUU6G4uJicjnbqdECHDkB2du39uDjAYATSHnEWFRUZDWJIJBJs2bIF9913n81OweSTnOQkp1M6nZ3ly5dj2rRpiI2Nxd69e7lNSfPy8vCvf/3LwdHZhjPVHWeJlZzkJCc5ySkcJ9HE4HEgQ8hXGAv5imXKm20IuayUt1rGdx0PANidvRsFyrsPrFPeHO9yJBbtkWEIYwwiE/sLXL16Fd7e3rwE1VRwcbE6veTk01l3EKN9eyA11Wh/DL7j1Ol0WLx4MXbt2gXgziCGNRt7m0IQ+SQnOcnptE5nx9XVFbNmzar3+Ouvv+6AaPjBmeqOs8RKTnKSk5zkFI6TaFrwuUeG/opgNzc3Qbns4eMTypttCLmslLdaYgJi0LN1TyRdS8I3J7/B670a/huP8uZ4lyMRMWbZN1K3bt0gEomQkZGBjh07GnV2tFotcnNzMXjwYHz33Xd2C5YPysvL4e3tjbKyMkikEngsrr2qUzlHCYWb849MEbdhrHY5Kf0U3PbtgTNnALHVk5Aspu5yUnwNYhAE0Xwx/M7y8vJydDj3lJ07d2LIkCFwdXXFzp07Gzz28ccfv0dR2UZzPo8EQRCEc0HfWU0Dvs9j7qOPou3u3cYP2ji4od9wViaTNTYsXl328O3atQvDhg3jxUV5sw0hl5Xv2AD+cnev87bq2Cr8a/e/0DmwMzKmZJi8gN5esQHOmzdHufTwlTdrvrMs/lV3xIgRGD58OBhjGDRoEIYPH87dRo8ejS+//BJff/11o4NvSiQnJ5PTUc6KCosGMfiK096DGA7PJznJSU6ndjojI0aMQElJCfd/c7cnnnjCwZHahjPVHWeJlZzkJCc5ySkcJ0GYQ6PRQKPRCM5lDx+fUN5sQ8hlpbzdYXSn0XCTuOHkjZNIz0+/p7HxCdU3+2PxHNJ58+YBAMLDwzFq1ChIpVK7BWUPVq5ciZUrV0Kr1QIAUlJSIHa/88P2sWPHEOgbiLZt2+LEiRMAgDZt2kCn0+HKlSsAgLi4OOTk5ECpVEKhUCAqKgrHjx8HAISEhEAikeDSpUsAgC5duqC8vBxJSUmQSqXo2LEjUlNTAQCtWrWCVCrFhQsXAACdOnXC1atXUVpaCjc3N8TFxXGdyeDgYHh4eCAnJwcAUFNTg+zsbBQXF8PFxQXdu3dHcnIyGGMICAiAr68vzp07BwCIjo5GcXExCgsLIRaL0aNHD6SkpECr1aJFixYIDAxEVlYWSkpKUFxcjPLycm6jt549eyItLQ0ajQa+vr5o1aoVMjMzAQARERGoqKhAXl4eACAhIQGnTp2CWq2Gt7c3wsLCUFxcjKSkJISHh6OmpgZXr14FAMTHx+PMmTOoqKiAh4cHIiIikJGRAQAICwsDAFy+fBkA0LVrV5w/fx5KpRJyuRxarRZJSUlcvl1cXHDx4kUAQOfOnXH58mWUlZVB6u6OTkFBkNw+t1d++gmy4mKcP38eANCxY0dcv34dJSUl3H4vem9QUBC8vLyQfXs5qpiYGNy4cQM3b96ERCJBQkICjh07Bp1Oh4CAAPj5+eHs2bNYu3YtN4ghFouxcOFCPP3000hNTUVNTQ38/PwQFBSErKwsAEBkZCSUSiXy8/MBAImJiUhPT0d1dTV8fHwQEhKCU6dOAQDatWuHiooKLsbu3bsjMzMTarUaXl5eCA8PN6qzWq2Wy3e3bt1w7tw5qFQqeHh4IDIyktsoTq1WIz8/36jO5ubm4tatW5DJZIiJiUFaWhoAoHXr1nBzc0Nubi6X7ytXrqC0tBTu7u7o0qULjh07hpKSEly6dAkKhYLLd2xsLPLz81FcXAxXV1fEx8dzZQkMDIS3tzeX7w4dOqCoqAhFRUVcnS0pKUFSUhL8/f3h7++PM2fOAADat2+PsrIy3Lhxo16d9fPzQ3BwME6fPs3VWZVKxeWbMYb09HRUVVXBx8cHoaGhOHnyJACgbdu2qK6uxrVr17g6m5WVhcrKSnh6epptI0pKSlBVVWVVG3Hx4kWUl5ebbSP0nyNr2oiYmBgUFBSYbSOqq6u5/FvaRujzba6NUCqVUCqVVrUR+nybayOKi4uRmZlpVRvRoUMHrs6aaiMM2+ROnTohJSUFANCyZUvI5XKTbUTdOlu3jdBoNMjJyblrGwEAUVFRKCkpQWFhIUQiERITE022ESUlJbh58yaUSiUXU3NEp9OZ/L8zYarvoVAoEB8fj7KyMiQlJTXYrgDW9T20Wi2ysrIabFeo72GnvocV7QpffQ/gTrtSXFyM5ORks+0KQH0P6ntQ34P6HtT3IGyHz6WlxDyuksCnyx4+PqG82YaQy0p5u4OvzBcjOozAd5nfYUPGBnRr2e2excYnVN/uAayZUVZWxgCwsrIypqxSMswHw3wwZZWS9/c6f/48Oe+1U6tlLC6OsdqJrrU3pflzy1echYWFrGvXrkwikbDPP/+cF6chTeockZOc5LTYafidRTgvps6js9RHe3nJSU5ykpOcwnRS36NpwPd5zB082Phv7Eb8lKRUKpmygb/RHeWyh2/nzp28uShvtiHksvIdG2P85c4Refvl3C8M88H8/+3Pqmqq7llsjDl33hzh0sNX3qz5zrJoRoafnx/OnTsHf39/+Pr6NrhWWXFxMQ/DK00DX19fct5LJ2NA9+53lpQCgD59ALncdqeF+Pv7448//sCxY8dw33338eI0pMmcI3KSk5wOcTo706dPR2RkJKZPn270+Oeff46cnBx8+umnjgmsEThT3XGWWMlJTnKSk5zCcRKEOfhedoVPhLzsCuXNNoRcVsqbMY9EPIJgj2DkK/OxO3s3RnQYcU9i4xOqb/bHonkly5cvh6enJ/f/hm7EHfTLLJDzHjlVKuN9MW7dAg4eBBoYeLM1Tp1OB5VKZfSYv78/hgwZ0nTySU5ykrPJOJ2dbdu2oU+fPvUe7927N3744QcHRNR4nKnuOEus5CQnOclJTuE4iaYFn0tLSaVS3pYq59NlDx+fUN5sQ8hlpbwZ4yJ2wfNdngcAbMjYcM9i4xOqb/bHohkZ48eP5/7/wgsv2CsWgrAdxoD7779zPy0N8PCwy1vpN/Y+c+YM9uzZAy8vL7u8D0EQBFHLzZs34e3tXe9xLy8vFBUVOSAigiAIgiCIZgSPAxmVlZUAwMsPany67OHjE8qbbQi5rJS3+ozvOh5LDi/Bz+d+RqGqEAGKALvHxidU3+yP1Tt9pKWlcRulAcBPP/2EESNG4J133kF1dTWvwTk70dHR5LxXTsPZGHFxgELReKcJ9IMY69atw5EjRzBs2LB6m9A2iXySk5zkbFJOZycyMhJ79uyp9/ivv/6Kdu3aOSCixuNMdcdZYiUnOclJTnIKx0kQ5lAoFFBY+Pf6vXTZw8cnlDfbEHJZKW/16RjYEQmtElCjq8E3J7+5J7HxCdU3+2P1QMbLL7/MTT29cOECRo0aBblcju+//x5vvfUW7wE6M/bYL4ScJtDpgPj4O/fvspyURU6Tb3NnEAMAJBIJXn31VYjFxh8jp88nOclJzibndHZmzpyJt956C/PmzcOBAwdw4MABzJ07F7Nnz8brr7/u6PBswpnqjrPESk5ykpOc5BSOk2hi8DgjQ6VS1VumWQgue/j4hPJmG0IuK+XNNC90fQEAsD5jfaNd9xqqb/bH6oGMc+fOIS4uDgDw/fff48EHH8Q333yD9evXY9u2bXzH59QUFhaS055OxgClEujQAcjOrn3MitkYJp1mMDWIsWXLFjz99NM2O62BnOQkJzmbMy+++CKWLVuGNWvWoF+/fujXrx++/vprrFq1CpMnT3Z0eDbhTHXHWWIlJznJSU5yCsdJNC343CNDyFcYC/mKZcqbbQi5rJQ30zzb+Vm4SdyQnp+OtLw0u8fGJ1Tf7I/VAxmMMW4pnT/++ANDhw4FAISGhtI61XWoe6U+OXl0Mgb07Qt4et4ZxGjfHkhNtXg2Rj2nGawZxLDUaS3kJCc5ydnceeWVV3D16lUUFBSgvLwcFy5cwLhx4xwdls04U91xlljJSU5ykpOcwnESTQyakeFwKG+2IeSyUt5M4yfzw5MxTwIA1qStsXtsfEL1zf6IGLPuG+nhhx9GaGgoBgwYgIkTJ+L06dOIjIzEgQMHMH78eFy8eNFOofJDeXk5vL29UVZWBolUAo/FtRtCK+cooXBz/pGpZoNSWTuIoScurnYQg+dOuLWDGARBEHxi+J3l5eXl6HAcSk1NDfbv34/z589jzJgx8PT0xPXr1+Hl5QUPDw9Hh9cgdB4JgiAIZ4G+s5oGfJ/HywMGIOzPP40ftHFwQ7/hrEwma2xYvLrs4du1axeGDRvGi4vyZhtCLivfsQH85c7Refvjwh8YuGkgvN29kfdGHmSud15HeXO8Sw9febPmO8vqX30//fRTpKWlYdq0aXj33XcRGRkJAPjhhx/Qu3dv2yJuoqSkpJCTb6d+OSnDPTEKCoC0NJsGMRqK09ZBDKfKJznJSc5m4XR2Ll26hM6dO2P48OGYOnUqtwTGJ598glmzZjk4OttwprrjLLGSk5zkJCc5heMkmhZ8Li2l0Wig0WgE57KHj08ob7Yh5LJS3szzcNuHEe4TjrKqMmzLMt7GgPLmeJcjsfqX3y5duuDkyZMoKyvDvHnzuMeXLFmCDRs28Bqcs6PVasnJF4yB3bpVO4BhuJxUXBwQEGDVclKGNBRnTU0Nt/GdNTMxnCKf5CQnOZuV09mZMWMGEhISUFJSYnQFyRNPPIE/614d6CQ4U91xlljJSU5ykpOcwnESTQweBzJEIhFENv79bk+XPXx8QnmzDSGXlfJmHrFIjIndJgIAvkr7yq6x8Ymj83avXI7ExdYXpqamIisrCwAQGxuLeMMr5AkAQIsWLcjJB7f3w+hx+LDx4/rlpBrxQWwoTjc3N3z33XcYO3YsRo0aZfFyUoLPJznJSc5m53R2Dh48iMOHD8PNzc3o8fDwcFy7ds1BUTUOZ6o7zhIrOclJTnKSUzhOgjCHRCIRpMsePj6hvNmGkMtKeWuYF+JewLz983Dg0gFk38xG+xbt7RIbnwghb/fC5UisnpFx48YN9OvXDz169MD06dMxffp0JCQkoH///txSD0QtgYGB5OSDigrAcBAjLg64dcvm5aQMuVuc+sEMa/bEEHw+yUlOcjY7p7Oj0+lMXi169epVeBrul+REOFPdcZZYyUlOcpKTnMJxEk0LPpeWqq6uRnV1teBc9vDxCeXNNoRcVspbw4R4hWBw5GAAwNrja+0WG58IIW/3wuVIrP4V+NVXX4VSqURmZiaKi4tRXFyMU6dOoby8HNOnT7dHjE6LfsYKOXlEvx+Gh0ejZmLoMYxTp9Nhzpw5yM3NNTrG2qlXzpJPcpKTnM3H6ew88sgj+PTTT7n7IpEISqUS8+bNw9ChQx0XWCNwprrjLLGSk5zkJCc5heMkmhg8DmTIZDLeNpvl02UPH59Q3mxDyGWlvN2dSd0mAQDWZ6yHRquxS2x8IpS82dvlSKxeWmrPnj34448/EBMTwz0WGxuLlStX4pFHHuE1OIKoh0LBywBGXQw39v7mm2+wf/9+tG3blvf3IQiCIKxn6dKlGDx4MGJjY6FWqzFmzBhkZ2fD398f3377raPDIwiCIAiCECSVlZUAai8CkUgkqK6uhkwmQ0VFBRQKBVQqFeRyOSorK+Hm5gatVgvGGFxdXaFWq7ljTA1kKJVK6HS6esfq/5XJZKiqquKWM9FqtXB3d8eNGzcglUrh6urKHSuVSqHRaCAWiyESiaDRaCCVSlFZWVnPqz9Wf2GLRqNBUFCQ1WUyjFOtVsPV1RWlpaVgjKFFixZWlclcnIwxKJVKq8pk7jxpNBqo1Wr4+/tbVSbGWL3zVFBQwJ0Da8tk6jw1dE5tqXuMMVRXV1tVJnPnqby8HFqtFgEBAVaVydyxN2/ehEgkgq+vr82fJ/2/+ivk/fz8rCpTQ+eJMYbKykqbPk+G58mwjtj6eTIsU2FhYb06YkmZHgl/BAGyAOQr8/HDiR8wrP0wi8+ptXWvsrLSps+T4bFVVVXQaDTw9fW1+fNkeKz+cx8QEGDz58nc596Wz1PdMjHGUFJS0ui2vKKiwuLvNatnZOgLVxdXV1fodDprdU2a9u3bk1PgtG/f3mgQAwCuXbuGkydPNsrJN+QkJznJ2ZwJDQ1FRkYG3n33Xbz++uvo1q0bPv74Yxw/ftxpl8NwprrjLLGSk5zkJCc5heMkHMPKlSsRGxuLHj16ODoUs0ilUsjlcl5ccrmc1yuM+fbxCZ+x8XkO7OHjEyFfIS+XyyGVSnlx8Y1Q6oirxBWjY0YDADad2gRA2HmzR5vEV1mF/Dm1BqtnZDz88MOYMWMGvv32W7Rq1QpA7Q+/r7/+Ovr37897gM5MeXk5/Pz8yClgSktLMWvWLG4QQyKRYMuWLXj88cdtdjpLPslJTnI2H6czo9Fo0KFDB/z8888YO3Ysxo4d6+iQeMGZ6o6zxEpOcpKTnOQUjpNwDFOnTsXUqVNRXl4Ob29vyGQyeHl5cc/rf8Ryd3cHULsnpOF9Q/Q/xrm5uaHCxIwMDw8Pk8ca/mvqBzj91eL6K5b1x5r68U//+rpe/bElJSVwcXGBu7u71WUyFWd1dTXEYrHRj9WWlMlcnCKRyChPlpQJMH2e9GWt+0OkNXHqj3V1dTU6B9aUydR5suScWlP3RCIR3NzcrCqTuWNLSkogkUgglUqtKpO5Y9VqNVceWz9P+n/151ShUFhVpobiFIlEZgdbrKl7deuILZ8nQ9Rqtck6YkmZpvaais/SPsNvub+hTFcGOZPDxcXF4nNqyXmqmzdb656+vtnyuTd1bElJCTeDwtbPkzWfe2vrnn52kjVlMnUss2L5QqtnZHz++ecoLy9HeHg4IiIiEBERgbZt26K8vByfffaZtbomTUFBATkFjE6nw4wZM+oNYlizsbcpnCWf5CQnOZuP05nRT3FtajhT3XGWWMlJTnKSk5zCcRKEOQx/ABaSyx4+PqG82YaQy0p5s4xo/2jcH3Y/dEyHDRkbKG8CcDkSq2dkhIaGIi0tDX/++Se3KVhMTAwGDBjAe3AEYS/0y0n9/PPPAPgbxCAIgiD4Z+rUqfjkk0/w1VdfwcXF6q4LQRAEQRAE0Rh43Oxbv2+HqSuHHemyh49PKG+2IeSyUt4sZ2K3iTh4+SDWHl+LKZ2mQCwSU94c6HIkImbF/I2tW7di586dqK6uRv/+/TFlyhR7xmYX9FMsy8rKIJFK4LG4drqPco4SCjfFXV5NOASVCtBPy1Iqazf8bgR198SgQQyCIISK4XeW4bIAzY0nnngCf/75Jzw8PNC5c+d6069//PFHB0VmGXQeCYIgCGeBvrOaBnyfx+t9+6LVoUPGD9o4uKHf1JWPK4P5dNnDt2vXLgwbNowXF+XNNoRcVr5jA/jLndDypqpWodV/WqG8qhy7R+3Gg2EPUt4c6NLDV96s+c6y+LLGVatWYerUqWjfvj1kMhl+/PFHnD9/HkuWLGl0wPeClStXYuXKldBqtQCAlJQUiN3vrKx17NgxBPoGom3btjhx4gQAoE2bNtDpdLhy5QoAIC4uDjk5OVAqlVAoFIiKisLx48cBACEhIZBIJLh06RIAoEuXLjh69Ci3MUvHjh2RmpoKAGjVqhWkUikuXLgAAOjUqROuXr2K0tJSuLm5IS4uDsnJyQCA4OBgeHh4ICcnh4vVz88PxcXFcHFxQffu3ZGcnAzGGAICAuDr64tz584BAKKjo1FcXIzCwkKIxWL06NEDKSkp0Gq1aNGiBQIDA5GVlYXS0lL06NED5eXl3LTinj17Ii0tjVs/rVWrVsjMzAQAREREoKKiAnl5eQCAhIQEnDp1Cmq1Gt7e3ggLC8PBgwfh4+OD8PBw1NTU4OrVqwCA+Ph4nDlzBhUVFfDw8EBERAQyMjIAAGFhYQCAy5cvAwC6du2K8+fPo+LGDei3Kjt27Bh0MhlCQkLg4uKCixcvAgA6d+6My5cvo6ysDFKpFJ06dUJKSgoAoGXLlpDL5Th//jwAICcnhxvEEIvF2LJlC0JDQ5GUlISgoCB4eXkhOzsbQO1soxs3buDmzZuQSCRISEiojUGnQ0BAAPz8/HD27FkAQFRUFEpKSpCdnQ1fX18kJiYiNTUVNTU18PPzQ1BQEDeLKTIyEkqlEvn5+QCAxMREpKeno7q6Gj4+PggJCcGpU6cAAO3atcOZM2e4NeS6d++OzMxMqNVqeHl5ITw83KjOarVaLt/dunXDuXPnoFKp4OHhgcjISKSnpwOoXXc+MjLSqM7m5ubi1q1bkMlkiImJQVpaGgCgdevWcHNzQ25uLpfvK1euoLS0FO7u7ujSpQuOHTuG0tJSdOjQAQqFgst3bGws8vPzUVxcDFdXV8THxyMpKQkAEBgYCG9vby7fHTp0QFFREYqKirg6+/vvv8Pb2xv+/v7w9/fHmTNnANRuSlhWVoYbN27Uq7N+fn4IDg7G6dOnuTqrUqm4fLu4uEAikaCqqgo+Pj4IDQ3lNnhv27Ytqqurce3aNa7OZmVlobKyEp6enmbbiNLSUjz00ENWtREXL15EeXm52TYiLS0NPj4+VrURMTExKCgoMNtGFBQUQCwWW9VG6PNtro2orKxEQkKCVW2EPt/m2ojr168jJCTEojZCqVRCLpejQ4cOXJ011UYkJSVxbXJDbUTHjh1x/fp1bj1Kwzpbt41gjMHf39+qNqKwsBAikchsG1FaWoqEhAQolUoupuaOj48PnnrqKUeHYTWm+h4KhQLx8fH4+++/4eHh0WC7AljX9xCJRPD09GywXaG+h2V9D327UlVVxZ2/xvQ9DNuV8vJyDBw40Gy7Qn0P6ntQ34P6HtT3IAQHjzMy9N+rQnPZw8cnlDfbEHJZKW+Wo3BTYEynMViduhpr09eib+u+PEXGL0LLm71cDoVZSGxsLJs/fz53f9OmTUwul1v6csFQVlbGALCysjKmrFIyzAfDfDBllZL39zp69Cg5G4tOx1hcHGO1XSfGlI0/Tzqdjs2ePZtJJBK2aNEiHoI0RtD5JCc5yelUTsPvLMJ5MXUenaU+2stLTnKSk5zkFKaT+h5NA77P4/Veve78Ta6/NSI2vuLi02UP386dO3lzUd5sQ8hl5Ts2xvjLnRDzlnIthWE+mPtCd3Yh/wJPkdXSlPNmD5cePvNm6XeWxZt9X7hwAePHj+fujxkzBjU1NdxVL0R99Du3k7MRVFQAt6/iU8fEADxMgRKJRFi0aBGOHz9ulyt8BZ1PcpKTnM3S6azodDp88skn6NOnD3r06IHZs2dza3s6O85Ud5wlVnKSk5zkJKdwnARhDldXV7i6ugrOZQ8fn1DebEPIZaW8WUf3Vt3RvWV3VGmrsPXMVp4i4xch5s0eLkdi8UBGVVWV0ZrUYrEYbm5uTeYHBXvQqlUrctoCY7X7Yuhvt6nZtw8QiazW6XQ6bkkAPSKRCJ07dxZe2clJTnKS0w5OZ+Wjjz7CO++8Aw8PD7Ru3RorVqzA1KlTHR0WLzhT3XGWWMlJTnKSk5zCcRJNDB6XllKr1VCr1YJz2cPHJ5Q32xByWSlv1jMloXav5q/Sv4KO6Rrt4xuh5o1vlyOxeCADAN5//33MnDmTu1VXV+Ojjz4yeoy4g37NVnJaAWNA3761m3t7eABBQdxTWXUGIyxBv7F3QkIC/vnnH/7ibABykpOc5BSa01nZuHEjvvjiC/z222/YsWMHdu3ahc2bN0OnE16n1Vqcqe44S6zkJCc5yUlO4TiJpoWIx4EMhUJhdJGsUFz28PEJ5c02hFxWypv1jO40Gl7uXjhfeh5/5f7FQ2T8ItS88e1yJBZv9v3AAw9wm4bp6d27N7dpJFB7lTtBNIqKCuDw4fqP9+kDnVRqlUo/iKHf2HvYsGHIzc2Fj48PD4ESBEEQ9uby5csYOnQod3/AgAEQiUTchqwEQRAEQRCEc6G6veqCm5uboFz28PEJ5c02hFxWypv1eLh54JmoZ7Dm5BqsTl2N/u368xEebwg1b3y7HInFAxn79++3YxhNk4iICHI2hoICQD9aKJcj4uZNi19adxBDIpHgq6++qjeIIdiyk5Oc5CQngZqaGkjrDGK7urpCo9E4KCL+cKa64yyxkpOc5CQnOYXjJJoYPM/IEKLLHj4+obzZhpDLSnmzjVcSX8Gak2uw48wO5CvzEewRzJu7sQg5b0Kub9Zg8UAGYT0VFRXktBbDDpJCcWcgwwqnqUGMrVu3mtzYW1BlJyc5yUlOOzmdFcYYXnjhBbi7u3OPqdVqTJkyxagj9uOPPzoivEbhTHXHWWIlJznJSU5yCsdJNDHMDWRkZgLTpwMLFtQuEW0BQr7CWMhXLFPebEPIZaW82UY7RTsktkxEcl4y1h5fi3fuf6fRTr4Qct6EXN+swao9MgjryMvLI6c1MAbcf3+jnNYMYtgc510gJznJSU6hOZ2V8ePHIzAwEN7e3tztueeeQ6tWrYwec0acqe44S6zkJCc5yUlO4TiJpsUlg6U+jXj0UWDfvgb/jq+LTCaDTCbjJS4+Xfbw8QnlzTaEXFbKm+2ul+NfBgD8N/W/0Oq0vHj5QOh5E2p9swaakUEIh4oKID299v9xcYBcbtXLrR3EIAiCIISNvj0nCIIgCIIgHMeN7t2BwYOBPXuMn7h0yWqXWq0GgHrLh9oCny57+PiE8mYbQi4r5c1215DwIfCV+uJS2SX8dv43DG1vZrD1HiP0vPHlciQixnhc7NAJKC8vh7e3N8rKyiCRSuCx2AMAoJyjhMKN3/XCtFotJBIJOS1FpQI8as8Hbt26838LnZMnT8ZXX30FwPJBDMGUnZzkJCc5TTgNv7O8vLx4fR/i3mHqPDpLfbSXl5zkJCc5ySlMJ/U9mgZ8n8ddu3Zh2K+/AqtW3XmQMUAkMr5vAfrlTfhYr51Plz18u3btwrBhw3hxUd5sQ8hl5Ts2gL/cOUPe3v/nfSw/uhzDooZh57M7G+VsTnkTYn2z5juLlpayI6dOnSKnNRh2fAw7RBY6H3jgAYhEIqtmYgim7OQkJznJaUcnITycqe44S6zkJCc5yUlO4TiJJoiJv9FtgTEGvq6n5dNlDx+fUN5sQ8hlpbw1zvVy99rlpX7J/gVXyq7w4m4szpA3Z8emgYyDBw/iueeeQ69evXDt2jUAwKZNm/DPP//wGpyzo5+2Q04LuMv+GJY4n3/+eWzYsMGq5aQEUXZykpOc5LSzkxAezlR3nCVWcpKTnOQkp3CcRBOk7kCGjT+I6XQ66HQ6HgLi12UPH59Q3mxDyGWlvDXOFe0fjX7h/aBjOnyV9hUv7sbiDHlzdqweyNi2bRsGDRoEmUyG48ePo6qqCgBQVlaGRYsW8R6gM2OPDUibrNOC/TEscT7//PNW7YkhiLKTk5zkJKednYTwcKa64yyxkpOc5CQnOYXjJJogPA1kuLq6wtXVlYeA+HXZw8cnlDfbEHJZKW+Nd+lnZfwv7X/QaDW8+BuDs+TNmbF6IOPDDz/E6tWr8b///c8oAX369EFaWhqvwTk7YWFh5LSFgwdNTls1dOp0OkyePBnr16+3/X0gwLKTk5zkJKcdnITwcKa64yyxkpOc5CQnOYXjJJoBNl7Zq1areZsFxKfLHj4+obzZhpDLSnlrvOuJmCcQIA9AnjIPP5/7mRd/Y3CWvDkzVg9knD17Fg888EC9x729vVFaWspHTE2GkydPktMWzKy9qXfqdDpMmjQJX331FV588cVGDWYIruzkJCc5yWkHJyE8nKnuOEus5CQnOclJTuE4iSYITzMyFAoFb5vN8umyh49PKG+2IeSyUt4a73KTuGFit4kAgFUpq3jxNwZnyZszY/VARnBwMHJycuo9/s8//6Bdu3a8BEU0QyzsBOkHMdatWwcAEIvF8PT0tGdkBEEQBEEQBEEQBNG8qTuQYeOMDJVKBZVKxUNA/Lrs4eMTypttCLmslDd+XC91fwkiiLD3wl6cLTrLy3vYijPlzVmxeiBj8uTJmDFjBpKSkiASiXD9+nVs3rwZs2bNwiuvvGKPGJ2W8PBwcpqCMUClunNTKoH4+Ls6w8LCjAYxJBKJVRt7Wx0nOclJTnI2ESchPJyp7jhLrOQkJznJSU7hOIkmCM3IcCiUN9sQclkpb/y42vq2xWNRjwEAvjj2BS/vYSvOlDdnxcXaF8yePRs6nQ79+/dHRUUFHnjgAbi7u2PWrFl49dVX7RGj01JTU0POujAG9O0LHD5s+nkzG33rdDq8/vrr2Lp1KwB+BjEajJOc5CQnOZuQkxAezlR3nCVWcpKTnOQkp3CcRDOgETMyAMDNza3RIfDpsoePTyhvtiHkslLe+HNNS5yGXed2YX3Genz48IfwdHfMyi3OljdnxOoZGSKRCO+++y6Ki4tx6tQpHD16FIWFhVi4cKE94nNqrl69Ss66qFQND2Kkpta70kO/nBTfgxgNxklOcpKTnE3ISQgPZ6o7zhIrOclJTnKSUzhOognC04wMmUwGmUzGQ0D8uuzh4xPKm20IuayUN/5cA9oNQFSLKJRXlePrE1/z8j624Gx5c0asHsjQ4+bmhtjYWCQmJsLDw4PPmIimik5nvIRUQUHtslL6W1oaIBbXeYmO9+WkCIIgCIIgCIIgCIKwAp72yKiqqkJVVRUPAfHrsoePTyhvtiHkslLe+HOJRWJM7TEVAPD5sc/BbBxobSzOljdnxOqlpfr16wdR3S8wA/bt29eogOzFypUrsXLlSmi1WgBASkoKxO53fjQ/duwYAn0D0bZtW5w4cQIA0KZNG+h0Oly5cgUAEBcXh5ycHCiVSigUCkRFReH48eMAgJCQEEgkEly6dAkA0KVLF3h4eCApKQlSqRQdO3ZEamoqAKBVq1aQSqW4cOECAKBTp064evUqSktL4ebmhri4OCQnJwOo3Vzdw8OD22C9ffv2yM7ORnFxMVxcXNC9e3ckJyeDMYaAgAD4+vri3LlzAIDo6GgUFxejsLAQYrEYPXr0QEpKCrRaLVq0aIHAwEBkZWVBp9OhuLgY5eXlKCgoAAD07NkTaWlp0Gg08PX1RatWrZCZmQkAiIiIQEVFBfLy8gAACQkJOHXqFNRqNby9vREWFgadToekpCSEh4ejpqYGVy9fRpdRoyC7nUtVVBQu3riBiMhIZGRkAKjdAwMALl++DADo2rUr/vzzT6OZGAsXLkRISAiuXbsGFxcXXLx4EQDQuXNnXL58GWVlZZBKpejUqRNSUlIAAC1btoRcLsf58+cBAB07dsT169dRUlICiUQCAEhKSgIABAUFwcvLC9nZ2QCAmJgY3LhxAzdv3oREIkFCQgKOHTsGnU6HgIAA+Pn54ezZ2s2EoqKiUFJSAp1Oh+TkZCQmJiI1NRU1NTXw8/NDUFAQsrKyAACRkZFQKpXIz88HACQmJiI9PR3V1dXw8fFBSEgITp06BQBo164dgoKCuBi7d++OzMxMqNVqeHl5ITw83KjOarVa7qqqbt264dy5c1CpVPDw8EBkZCTS09O5epifn29UZ3Nzc3Hr1i3IZDLExMQgLS0NANC6dWu4ubkhNzeXy/eVK1dQWloKd3d3dOnShcvLpUuXoFAouHzHxsYiPz8fxcXFcHV1RXx8PFeWwMBAeHt7c/nu0KEDioqKUFRUxNVZkUiEpKQk+Pv7w9/fH2fOnOE+C2VlZbhx40a9Ouvn54fg4GCcPn2aq7MqlYrLd1xcHNLT01FVVQUfHx+Ehobi5MmTAIC2bduiuroa165dAwDEx8cjKysLlZWV8PT0NNtG6HQ6VFVVWdVGXLx4EeXl5WbbCP3nyJo2IiYmBgUFBWbbiHbt2nH5t7SN0OfbXBvh5eUFpVJpVRuhzzfXRtyus/Hx8Thz5gx0Oh0yMzMRERHRYBtx/vx5KJVKyOVydOjQgauzISEh9doIwzbZ0jaibp2t20ZERkYiJyfHqjaisLAQIpHIbBuh0+lw8+ZNKJVKLibCOTHV91AoFIiPj4e7uzuSkpIabFcA6/oeMTExyMrKarBdaVZ9jzrtSkVFBTw8PKxqVzp37sx9/k21K9T3oL4H9T2o70F9D6LZwNOMDP33IB/w6bKHj08ob7Yh5LJS3vh1je86Hu/8+Q5OF57G/ov70a9tP97e01KcMW/OhohZOUz1+uuvG93XaDRIT0/HqVOnMH78eKxYsYLXAPmmvLwc3t7eKCsrg0Qqgcfi2tkkyjlKKNz43fTk5MmT6Ny5MzkZq52JcfuPWLRvD5w5U2/2hTkOHz6Mxx57DO+99x5mzpxpvzjJSU5yklNgTsPvLC8vL17fh7h3mDqPzlIf7eUlJznJSU5yCtNJfY+mgf485ufnQyaTQSQSQSKRoLq6GjKZDBUVFVAoFFCpVJDL5aisrISbmxu0Wi0YY3B1dYVareaOOXjwIB757TdIv7izka7y6lV4hIRw96urqqBSqbjXyGQyVFVVcT+eabVauLu7o7i4mFveRH+sVCqFRqOBWCyGSCSCRqOBVCpFZWUld0zdY0UiEdRqNTQaDVq0aGF1mQzjVKvVcHV1hUqlgk6ng7e3t9ljTZXJXJx79+7Fww8/bFWZzJ0nxhjUajV8fHysKhNjDDqdzujYoqIi7hxYWyZT56mhc2pL3du7dy8GDx5sVZnMnaeKigpotVr4+vpaVSZzx5aVlUEkEsHT09Pmz5P+X51Oh+rqanh5eVlVpobO0549ezBw4ECbPk+G5+nmzZvcObX182RYppKSknp1xNa6V1lZiZqaGpPn9JWfX8Hak2sxLHIYNj++2eK699dff2HgwIE2fZ5MnVNPT0+bP0+GxwJAZWUlfH19bf48mfvc2/J5qlumgwcP4v777290W65SqdCyZUuL+h5Wz8hYvny5ycfnz58PpVJpra5JU1FRQU6gdl8MGwcxAKB3797Izc3lrobjE6fMJznJSU5yEk6PM9UdZ4mVnOQkJznJKRwn4RjqzgblFZ6WltJqtdBqtbxcHazT6aCzMQ5TaLVaXn18wmdsfJ4De/j4hO9zyrfLLp9VHhByHdG7TDGxy0SsPbkWv5z/BVfKryDcN7zR72dtbHy3SXzVESF/Tq3B6oEMczz33HNITEzE0qVL+VI6PfbYO8TpnIwB999/5wkT+2AYotPpsG3bNjz99NNGS5h5e3s7X9nJSU5yklMgTkJ4OFPdcZZYyUlOcpKTnMJxEo5h6tSpmDp1KjcjQyaTGV3dKpfLAQDu7u4Aavc+NbxviP7KXTc3N4hEIkjrbBLroTBe0cLNzY3z6f+VSqX1vAEBAUbP6Y81tQlt3WPqHuvq6srFb22ZTMWp/4FPKpXe9VhL4hSJRPU+X3crE2D6PKnVanh6etZ7f2vi1B9b9xxYUyZT58mSc2pN3ROJRBbXp7uV38XFhbtvTZkaOqf65239POn/5eOc1o1TJBKZ3dTZmrpX95za8nkyxFwdsaXuNXROe0f2Rr/wfvjr4l/YfGYzPur/kUXnqW7ebK17arXa5PG21j21Wg0PDw+jNgmwrS235HNvbd0TiUTw9fW1qkymjrVmsSibN/uuy5EjR0wWrDkTERFBTsPZGHFxgML88l36jb1HjhyJt956q15Fdrqyk5Oc5CSnQJyE8HCmuuMssZKTnOQkJzmF4ySaIDzNyKisrERlZSUPAfHrsoePTyhvtiHkslLe7OOaljgNAPDftP9CXaPm5T0txZnz5ixYPZDx5JNPGt2eeOIJ3HfffZgwYQJefvlle8TotOg3iWu2zrqzMQ4erN/5uY1+EGPdunUAapcw02/IZ/c4yUlOcpKziTsJ4eFMdcdZYiUnOclJTnIKx0k0QepeMWvjZt8KhQKKBi5wdJTLHj4+obzZhpDLSnmzj+vx6McR4hWCoooifJ/5PS/vaSnOnDdnweqBDG9vb6Obn58fHnroIezevRvz5s2zR4yEs2LhbIy6gxgSiQRbt25Fly5d7k2cBEEQBEEQBEEQBEGYp+4MDBtnZKhUKm4T28bCp8sePj6hvNmGkMtKebOPy0XsglcSXgEAfH7sc17e01KcOW/OglV7ZGi1WkyYMAGdO3fm1sAizBMWFtb8nIwBFRVo06IFEB9/53EzszHMDWI89dRT9o2TnOQkJzmbkZMQHs5Ud5wlVnKSk5zkJKdwnEQzoO6MjJISwILfifi+WplPhHy1MuXNNoRcVsqb/VyT4idhwYEFSL6WjORryUhsncjb+zeEs+fNGbBqRoZEIsEjjzyC0tJSO4VDODWMAX37Ah4eCG7fHsjOrn3czGwMawYxCIIgCIIgCIIgCIJwEHUHLurOyHj6aYs0Qr7CWMhXLFPebEPIZaW82c8VqAjEqI6jAACfJX/Gy/tagrPnzRmwemmpTp064cKFC/aIpclx+fLl5uFkrHYZqcJC4PBh4+fi4oDU1HqzMWwZxBBk2clJTnKS0wmchPBwprrjLLGSk5zkJCc5heMkmiB32yNj3z6LNFKpFFKplJeQ+HTZw8cnlDfbEHJZKW/2dU3vOR0AsPXUVuTdyuPlve9GU8ib0LF6IOPDDz/ErFmz8PPPPyMvLw/l5eVGN6KZYTALA0FB3MOpu3cDSiWQlgaI61ez9957j2ZiEARBEARBEARBEIQzwNNm3xqNBhqNhoeA+HXZw8cnlDfbEHJZKW/2dSW0SkDfsL7Q6DT44tgXvLz33WgKeRM6Fg9kfPDBB1CpVBg6dCgyMjLw+OOPIyQkBL6+vvD19YWPjw/tm1GHrl27Nn1nRUX9WRh9+qDjQw/VLidlYl8MAHjppZcQHh5u1SCG4MpOTnKSk5xO4iSEhzPVHWeJlZzkJCc5ySkcJ9EEudvSUhYiFoshNnGxo6Nd9vDxCeXNNoRcVsqb/V2v9XwNALA6dTUqNZW8vH9DNJW8CRmLS7BgwQKoVCr89ddf3G3fvn3cTX+fuMP58+ebl7OgoHYWxsGDOH+X5cfCw8Px119/Yfv27RbPxBB02clJTnKSU8BOQng4U91xlljJSU5ykpOcwnESTRCeZmSIRCKIzFzw6EiXPXx8QnmzDSGXlfJmf9eIDiMQ7hOOoooibD65mZf3b4imkjch42Lpgez2l9SDDz5ot2CaGkqlsnk5FQpuU++6Tp1Oh5qaGri5uXGPhYeHIzw83GK9oMtOTnKSk5wCdhLCw5nqjrPESk5ykpOc5BSOk2iC8DQjg+9lV/hEyMuuUN5sQ8hlpbzZ3yURS/Bq4qt44/c38OnRTzGx20S7/pjfVPImZKyaU9IURm7uJXK5nJy4s7H3U089haqqKl6cfEFOcpKTnM3BSQgPZ6o7zhIrOclJTnKSUzhOoglSdyBDq7VJI+TNa4W8GS7lzTaEXFbK271xTew2ER5uHsgszMQfF/7gJQZzNKW8CRWrBjKioqLg5+fX4I24Q4cOHZq9Uz+IsW7dOvz888949tlnudk9tjr5hJzkJCc5m4OTEB7OVHecJVZykpOc5CSncJxEE6Tu3/E2Xt1bWVmJykp+1qrn02UPH59Q3mxDyGWlvN0bl7fUGy/GvQgAWH50OS8xmKMp5U2oWDWQsWDBAixfvrzBG3GHtLS0Zu00HMQAAIlEgrFjx9o8s8eZyk5OcpKTnEJyEsLDmeqOs8RKTnKSk5zkFI6TaILwNJChUCiguL0kdWPh02UPH59Q3mxDyGWlvN071/Se0yGCCL/m/IozRWd4icMUTS1vQsSqgYzRo0dj/PjxDd5sYeXKlQgPD4dUKkXPnj2RnJxs9tj//e9/uP/+++Hr6wtfX18MGDCgweMJO2NmdoWpQYytW7davLE3QRAEQdgT6nsQBEEQBEFYAU8DGSqVCiqVioeA+HXZw8cnlDfbEHJZKW/3zhXhF4HHox8HAPxf0v/xEocpmlrehIjFAxn22h9j69atmDlzJubNm4e0tDR07doVgwYNwo0bN0wev3//fjz77LP466+/cOTIEYSGhuKRRx7BtWvX7BJfYwgJCWnaTp0OiI838bAOK1as4H0QQ1BlJyc5yUlOJ3ISxgih7+FMdcdZYiUnOclJTnIKx0k0QWhGhkOhvNmGkMtKebu3rtfuew0AsCFjA4ori3mJpS5NMW9Cw+KBDFv3Nbgb//nPfzB58mRMmDABsbGxWL16NeRyOdauXWvy+M2bN+Nf//oX4uLi0KFDB3z11VfQ6XT4888/7RJfY3BxcWmaTsYApRLo0AHIzq59LC4OkMu5mRhbt24FwO9MDEGUnZzkJCc5ndBJGCOEvocz1R1niZWc5CQnOckpHCfRBKn7m9Ajj9ikEfIVxkK+YpnyZhtCLivl7d66HmzzIOKC41ChqcD/Uv/HSyx1aYp5ExoWD2TodDoEBgby+ubV1dVITU3FgAED7gQkFmPAgAE4cuSIRY6KigpoNBqzG41XVVWhvLzc6HavuHjxYtNzMgb07Qt4et4ZxGjfHkhNhY4xuy4n5fCyk5Oc5CSnkzqJOwil7+FMdcdZYiUnOclJTnIKx0k0QeoOZNy6ZZNGKpVCKpXyEBC/Lnv4+ITyZhtCLivl7d66RCIRXuv5GgDgs+TPoNHaNqusIZpi3oSGQy+9KCoqglarRVBQkNHjQUFBOHPGss1X3n77bbRq1croBwlDFi9ejAULFtR7PCUlBWL3O+M4x44dQ6BvINq2bYsTJ04AANq0aQOdTocrV64AAOLi4pCTkwOlUgmFQoGoqCgcP34cQO10XIlEgkuXLgEAunTpglu3biEpKQlSqRQdO3ZEamoqAKBVq1aQSqW4cOECAKBTp064evUqSktL4ebmhri4OG7t7eDgYHh4eCAnJwcAUFNTg+zsbBQXF8PFxQXdu3dHcnIyGGMICAiAr68vzp07BwCIjo5GcXExCgsLIRaL0aNHD6SkpECr1aJFixYIDAxEVlYWSkpKUFxcjPLychQUFAAAevbsibS0NGg0Gvj6+qJVq1bIzMyEuKICPQ4f5vKmioqC9NQpnDp5EiUlJcjIyABQ+6PQwoUL0bdvX1y7dg1Xr14FAMTHx+PMmTOoqKiAh4cHIiIiuNeEhYUBAC5fvgwA6Nq1K86fPw+lUgn57dkeSUlJXL5dXFy4Tnfnzp1x+fJllJWVQSqVolOnTkhJSQEAtGzZEnK5HOfPnwcAdOzYEdevX0dJSQnKysoAgPMGBQXBy8sL2bcHaWJiYnDjxg3cvHkTEokECQkJOHbsGHQ6HQICAuDn54ezZ88CAKKiolBSUoKSkhIkJycjMTERqampqKmpgZ+fH4KCgpCVlQUAiIyMhFKpRH5+PgAgMTER6enpqK6uho+PD0JCQnDq1CkAQLt27VBZWcnF2L17d2RmZkKtVsPLywvh4eFGdVar1XL57tatG86dOweVSgUPDw9ERkYiPT0dAKBWq5Gfn29UZ3Nzc3Hr1i3IZDLExMRwG/+1bt0abm5uyM3N5fJ95coVlJaWwt3dHV26dMGxY8dQUlKCS5cuQaFQcPmOjY1Ffn4+iouL4erqivj4eK4sgYGB8Pb25vLdoUMHFBUVoaioiKuzpaWlSEpKgr+/P/z9/bm2oX379igrK+OWgjGss35+fggODsbp06cBABEREVCpVFy+GWNIT09HVVUVfHx8EBoaipMnTwIA2rZti+rqam7JmPj4eGRlZaGyshKenp5m24iSkhJUVVVZ1UZcvHgR5eXlZtuIkpISJCUlWdVGxMTEoKCgwGwbodFouPxb2kbo822ujVAqlVAqlcjMzOTyXVFRgby8PABAQkICTp06BbVaDW9vb4SFhXH5Dg8PR01NTb02oqSkBJmZmVa1ER06dODqrKk2wrBNtrSNqFtn67YRGo0GOTk5VrURhYWFEIlEZtuIkpIS3Lx5E0qlkouJ4A9H9z0UCgXi4+NRXl6OpKSkBtsVwLq+h1arRVZWVoPtijP2PQDL2hV9m2muXaG+B/U9AOp7UN+D+h7U9yAcjeb2klQymUxQLnv4+ITyZhtCLivl7d67Rncajbf/eBvXbl3DtqxtGN1pdKPj4Ss2e/uEXN+sQcTstWaUBVy/fh2tW7fG4cOH0atXL+7xt956CwcOHOA6b+b4+OOP8e9//xv79+9Hly5dTB5TVVWFqqoq7n55eTlCQ0NRVlYGiVQCj8UeAADlHCUUbvyuFVZRUQG5XN50nIzV7olx+49RFBQAAQGAwf4pt27dwuOPP47JkydjzJgxjomTnOQkJzmbiLO8vBze3t4oKyuDl5cXr+/TXHF030N/Hp2lPtrLS05ykpOc5BSmk/oeTQO+z+OuXbswbOdO4KuvGj7Qgp+Xbt2eyeHp6dnouPh02cO3a9cuDBs2jBcX5c02hFxWvmMD+MtdU87bBwc+wLz985DYOhFHJx6FSCSivNkIX3mz5jvL4qWl7IG/vz8kEgl3lY2egoICBAcHN/japUuX4uOPP8bvv/9u9ocEAHB3d4eXl5fR7V6hv3KnyTgrKu4MYsTF1RvEAGo/EPv27UO8iU3AG0uTyyc5yUlOct4jJ3EHofQ9nKnuOEus5CQnOclJTuE4iSaITseLRiKRQCKRCM5lDx+fUN5sQ8hlpbw5xjUlYQrcJe5IvpaMfy7/w0tMeppy3oSCQwcy3Nzc0L17d6PNMvWbZxpeJVmXf//731i4cCH27NmDhISEexGqTeiXDmiSzoMHoWMMH3zwAQoLC42eEolEwomTnOQkJznJSRgglL6HM9UdZ4mVnOQkJznJKRwn0QThaTGP6upqVFdXC85lDx+fUN5sQ8hlpbw5xhWoCMT4ruMBAEsOL+ElJj1NOW9CwaF7ZADAzJkzMX78eCQkJCAxMRGffvopVCoVJkyYAAAYN24cWrdujcWLFwMAPvnkE8ydOxfffPMNwsPDuXVnPTw84OHh4bBymMIem6g4xMlY7WwMg93tDTf2/v7777Fv3z4EBAQ4Nk5ykpOc5CQnYQFC6Hs4U91xlljJSU5ykpOcwnEShDn4XJ+d77Xehbx2POXNNoRcVsqb41xv9H4D/0v7H3ad24WswiweoqqlqedNCDh0RgYAjBo1CkuXLsXcuXMRFxeH9PR07Nmzh9uE8/Lly9ymbQCwatUqVFdX4+mnn0bLli2529KlSx1VBLN06tTJ+Z2MAX37Ah4ewO1zogMwaepUrFu3DgCQlZXFbVznsDjJSU5ykpOchIUIoe/hTHXHWWIlJznJSU5yCsdJNEF4mpFRUVGBiooKwbns4eMTypttCLmslDfHuaJaRGFEhxEAgKWH+fs9uannTQg4fCADAKZNm4ZLly6hqqoKSUlJ6NmzJ/fc/v37sX79eu7+xYsXwRird5s/f/69D/wu1P1x3+mcjAGFhcDhw9xDOgCTAgOxbtMmALVrrG3duhVDhgxxXJzkJCc5yUlOwkoc3fdwprrjLLGSk5zkJCc5heMkmiA87ZGhUCigUCgE57KHj08ob7Yh5LJS3hzrerP3mwCAr09+jWJNcaN9QPPIm6Nx+NJShEDR6YDu3e9s7g1Al5eHSW+9VW8Q46mnnnJQkARBEARBEARBEARBmKKyshJA7T6WEokE1dXVkMlkqKiogEKhgEqlglwuR2VlJdzc3KDVasEYg6urK9RqNXcMYwxV1dVwv8v7lZSUcK+RyWSoqqriNpfVarVwd3fHjRs3IJVK4erqyh0rlUqh0WggFoshEomg0WgglUpRWVnJHVP3WJFIBKVSCY1Gg6CgIKvLZBinWq2Gq6srSktLwRhDixYtzB5rqkzm4mSMQalUWlUmc+dJo9FArVbD39/fqjIxxqDT6YyOzc/P586BtWUydZ4aOqe21D3GGKqrq60qk7nzVF5eDq1Wi4CAAKvKZO7YmzdvQiQSwdfX1+bPk/5f/Z4Ffn5+VpWpofPEGENlZaVNnyfD81RQUMCdU1s/T4ZlKiwsrFdHbK17lp7Tu9W9GM8Y9GrdC0euHcGuG7swsnKkTZ8nw2Orqqqg0Wjg6+tr8+fJ8Fj95z4gIMDmz5O5z70tn6e6ZWKMGbX7trbl1swUEcSMjKZKy5YtndPJWP1BjN69MWnOHIsHMZy27OQkJznJ2QSdhPBwprrjLLGSk5zkJCc5heMkHMPKlSsRGxuLHj168C/naWkpqVTK21rtMpmM1z1e+PbxCZ+x8XkO7OHjE6lUyus55dMn5Pom5DrCZ95e6/EaAGBP0R7cqrrVaJ+Q2yQhf06tgWZk2BG5XO6czoqKO4MY7dtDl5KCSTNmYN3tZTYsmYnhtGUnJznJSc4m6CSEhzPVHWeJlZzkJCc5ySkcJ+EYpk6diqlTp6K8vBze3t6QyWTw8vLintefa3f32rkVbm5uRvcN0f/g5ebmBpFIBHdX17u+v/4qZL3X1A9warUaWq223rGmfmDTv15/TN1jS0tL4ebmBnd3d6vLZCpO/ZXEMpnsrsdaEqdIJIKHh4dVZQJMnyd9Wet+Xq2J0/BYw3NgTZlMnSdLzqk1dU8kEsHNzc3qMpk6trS0FGKx2GgAwpIymTu2qqqKK4+tnyf9v6WlpdwMBWvK1FCcIpHIqP5aUiZT56luHbHl82RIVVWVyTpiS93T583Sc9rQeXra+2lEH4zG2ZtnsTlrM17v9brFZWronNryuTd1rP5zX/ec2lr37va5t7bu6WcnWVMmU8cyKwbKaUaGHTl//rxzOg0rUFoaNmzbZtUghkknD5CTnOQkJzmJpoIz1R1niZWc5CQnOckpHCfRBLF0j4x//jFa3aEuhj9QNxY+Xfbw8QnlzTaEXFbKm+NdYpEYb/R6AwCw/OhyaLSaRvmaS94cCQ1kELUDFypV7U2pBOLj7zwnEmHcuHEYP3487YlBEARBEARBEARBEIRpCgqA++8HunUze4hWq4VWq+Xl7fh02cPHJ5Q32xByWSlvjncBwPNdn4ePiw+ulF/B1sytjXI1p7w5ChrIsCMdO3YUtpMxQKlEwssvAx4etTdPTyA7u/b5uDhALodEIsGaNWtw+PBhiwcxBF92cpKTnORsRk5CeDhT3XGWWMlJTnKSk5zCcRJNkLst/dGyJXD58p37ZmZwMMasWkak4ZD4c9nDxyeUN9sQclkpb453AYDURYrHAh8DACw5vKRR7uaUN0dBAxl25Pr168J16nS1My88PSE5ccL4KQCXY2OB1FRAJAJQu6RUYmLivY+TnOQkJznJSTRBnKnuOEus5CQnOclJTuE4iSaIuR/A9Ouha7W1Nz01NSYPd3V1hasF+21YAp8ue/j4hPJmG0IuK+XN8S49Q/2HQuGqwImCE9h7Ya/NnuaWN0dAm33fBa1WC43GtjXSSkpKoFareY2HFydjwJNPAiUlQJs2tY/FxABffw0dgPc++AD7Dx7E+lOnEBUV5bg4yUlOcpKzGThdXV0hkUiMnETTxx7n2V51x1liJSc5yUlOcgrHSTRBzA1kuLsDlZW1AxeGszA0GsDEeuz6vrOpDWGthU+XPXx8QnmzDSGXlfLmeJceDxcPTIqfhBVJK7Dk8BI8EvGIIGITet4cAQ1kNIBSqcTVq1dtnnojlUqRm5vLa0y8OHU6YMaM2v+7uKC6RQu4SaVgBQUoLi7GI0OG4JEhQ1BQUACJRAKx2PqJO4ItOznJSU5yCswpEokQEhICDw8PAGgSV0kQd8ce59ledcdZYiUnOclJTnIKx0k0QRoayABqZ2PUHcgwgUKh4C0kPl328PEJ5c02hFxWypvjXYa8ft/r+Dz5c/xx4Q+k5aUhvmX83V9Uh+aYt3sNDWSYQavV4urVq5DL5QgICIDo9hJLTQKttvaKCaB2JoZEAsYYrl+/DqlUCqlUCgAIDQ2Ft7e3AwMlCIJo2jDGUFhYiKtXr6J9+/aQSCSIj7e+w0Q4H/Y4z/aqO84SKznJSU5yklM4TqIJYm4g4/bvB/WWljIzkKFSqQAAbiZma1gLny57+PiE8mYbQi4r5c3xLkPa+LTBqE6j8M3Jb/DxPx/ju2e+c3hszpC3ew0NZJhBo9GAMYaAgACbp90olUruClu+aJSTsdorJAyWMIFUCmVlJYqKioymFEdERMDX19cxcZKTnOQkZzNyBgQE4OLFi9BoNJBIJEhKSkLPnj15ipAQKvY4z/aqO84SKznJSU5yklM4TqIJcrcZGTU1xoMXNCODVyhvtiHkslLeHO+qy9t93sY3J7/BD6d/wNmis4j2j7bq9c01b/cS2uz7LjSZmRiMAWfPAsePAxkZdx4GkJeXh6KiIu6xxg5iEARBEJbTZL5nCIIgCIIgiKaLJUtLVVXdebyBGRn6K4MbC58ue/j4hPJmG0IuK+XN8a66dAnqgmFRw8DA8MmhT6x+fXPN272EBjLsiMPWL2XszrRO/a2mBlAqjQ/z8MCly5dRVlbGPcbXIIazrN1KTnKSk5xCcwYFBfHuJISHPc6zveqOs8RKTnKSk5zkFI6TaIJYsrSUBQMZMpmMt81m+XTZw8cnlDfbEHJZKW+Od5ninfvfAQBsOrEJl8suW/Xa5py3ewUNZNgRieESTvfKaTjzwvBmMAsDXbuCdeuGS1Ipim7e5B7mcyaGQ8ouQOeOHTsQGRkJiUSC1157DevXr4ePj0+jnHxBTuvZv38/RCIRSktLeXM2RENOkUiEHTt2WOx64YUXMGLEiLvG+fzzz2PRokUWewFhnSOhOffs2YO4uDjoDDc+vAteXl6NDYtwAuxxnu1Vd5wlVnKSk5zkJKdwnEQT5G4zMnQ6QK2+87iZgQy1Wg214XGNgE+XPXx8QnmzDSGXlfLmeJcp7gu5D/3C+6FGV4Olh5da9drmnLd7RbPZI2PlypVYuXIltLc3n0pJSYHY/c44zrFjxxDoG4i2bdvixIkTAGrXD6uurkZNTQ0AQC6Xo6qqClqtFhKJBO7u7qioqABQu1mKSCRC1e0rEORyOSoqKiAWiyEWiyGTyYw2VjE8ViaTQaPRoKampt6xrq6ukEgkRpXNxcUFNTU1EIlEUCgUUKlUYIzB1dUVkydPRvnly9ix1PSHTSuTobKqCi4uLkYbvISHh0Mul0N5e9aGh4cH53VxcYGrqysqb28Q7u7uDp1OB83tjolCoUB4eDguX77Mladt27Z45ZVX8PLLL4Mxhurqai4varUaOp3OZA4BGB2rz7dYLDb6IdDNzQ2ffvopFi9ejOzsbPj6+qK6upo7ljGGli1b4v3338f06dMRHR2NV155BVOnToVMJkO7du24ePW0atUKFy5cMMq34bnx9PTE9u3bMXDgQC7fhsdKpVJotVqo1Wq4uLhAoVDgpZdewnPPPYdp06bBz88PW7ZsAQDU1NRAq9Ua5bCyshI6nc5kvtVqNbf8jOGxdXPo7u5eL9/m6ixjDFKp1KjOGuZbKpWard8ymQxr167FSy+9BKD2R/XAwED07t0bn3zyCcLDw03Wb32d1dczUzmsqampV78lEglcXFzg4uJSL9/6HFpTZwFwdcrUsebqrL5MSqUSLi4uRsdqtVp4enriq6++wssvv4zo6GicPn3aKIfbtm3DmDFjEBYWhtzcXKN8m2ojKioqIJFITLYRAFBZWYmqqiqzddYwhxqNBjqdDpWVlVxdMsyhSCRCTk4Odu/ejSVLlkCtVhvlZceOHRg/fjwmTpyI//znP0b53rRpE+bMmYOrV6/Wy7enpyd+/PFHDBo0iKuzP//8M/7v//4PJ06cgFarRdu2bTF8+HC89NJLCAkJgVqthkajgZubm1VtREN1dvny5fj5559x8uRJuLm5oaSkxKidFYvF9eqsRqPBRx99hA0bNqC0tBT33XcfPv/8c0RHR3P5vnnzJt5++23s3r0bYrEYTz31FBYtWgSFQgFXV1cMGDAAEokEa9aswYQJE4zyrT83+vIqlUpkZGSgpKQEPXr0gFKpxPnz50E4L6b6HgqFAvHx8UhNTYWXlxc8PT2N+h5t2rSBTqfDlStXAABxcXHIycmBUqmEQqFAVFQUjh8/DgAICQmBRCLBpUuXAABarRa+vr4oLy+HVCpFx44dkZqaCqD2O04qleLChQsAgE6dOuHq1asoLS2Fm5sb4uLikJycDAAIDg6Gh4cHcnJyANR+ZwUGBqK4uBguLi7o3r07kpOTub3EfH19ce7cOQBAdHQ0iouLUVhYCLFYjB49eiAlJQVarRYtWrRAYGAgsrKyUFJSgsTERJSXl6OgoAAA0LNnT6SlpUGj0cDX1xetWrVCZmYmgNqLLSoqKpCXlwcASEhIwKlTp6BWq+Ht7Y2wsDAkJyfD19cX4eHhqKmp4dqk+Ph4nDlzBhUVFfDw8EBERAQybl/gERYWBgBcn6Br1644f/48lEol1y8Si8Vcvl1cXHDx4kUAQOfOnXH59sxWqVSKTp06ISUlBQDQsmVLyOVy7jPcsWNHXL9+HSUlJSgrK8MjjzyCpKQkALVXQnt5eSE7OxsAEBMTgxs3buDmzZuQSCRISEjAsWPHoNPpEBAQAD8/P5w9exYAEBUVhZKSEpw7dw5+fn5ITExEamoqampq4Ofnh6CgIGRlZQEAIiMjoVQqkZ+fDwBITExEeno6qqur4ePjg5CQEJw6dQoA0K5dO2RmZnLfN927d0dmZibUajW8vLwQHh5uVGe1Wi2X727duuHcuXNQqVTw8PBAZGQk0tPTAdT+ARUdHc3V2S5duiA3Nxe3bt2CTCZDTEwM0tLSAACtW7eGm5sbcnNzuXxfuXIFpaWlcHd3R5cuXXDs2DGUlJQgJiYGCoWCy3dsbCzy8/NRXFwMV1dXxMfHc/kODAyEt7c3l+8OHTqgqKgIRUVFXJ09duwYfHx84O/vD39/f5w5cwYA0L59e5SVleHGjRv16qyfnx+Cg4Nx+vRprs6qVCou34b9Lh8fH4SGhuLkyZMAgLZt26K6uhrXrl3j6mxWVhYqKysbbCNKSkrQr18/i9uILl264OLFiw22EampqfD19bWqjYiJiUFBQYHZNuL69evcDEZL2wh9vs21EUqlEj179rSqjdDn21wbce3aNYSGhlrVRnTo0IGrs6baiLS0NHh6elrVRtSts3XbCI1Gg+DgYKvaiMLCQohEIrNtBPU9CIu420AGANz+2wGA2YEMPmc08z072h6zrfmC8mYbQi4r5c3xLnO8c/87+OviX/hf2v/w3gPvIVARaNHrmnve7gmsmVFWVsYAsLKyMqasUjLMB8N8MGWV0ui4yspKdvr0aVZZWWnze926daux4Vru1OkYq6lh459/ng1/8EHGjh1jrLqasZoa45tOZ/SyvLw8dv369UbH1aZNG/bBBx+wvLw8dv78ebZgwQIGgO3evbvRbj11y15QUMBcXV3Z5s2b6x27YcMG5u7uzm7evMnFt3z58nrx5uTksLy8PJaXl8du3LjR4PsDYNu3b7c4zlu3bjEAbN++fdxz69atY97e3nd1mHPySWOd69atY15eXlwdOnToEOvcuTNLTEzkKcJahFT2v/76iwFgJSUlZp3r1q1jCoWC+fn5scOHDxsdM2jQIBYWFsbatGnT6DgtrY96xo8fz4YPH96gc+LEiezll182+Vz//v3Z7Nmzma+vb712cdWqVWbrdd0433nnHSaRSNisWbPYoUOHWG5uLvv999/Zk08+yT799FPuOL7P+9y5c9nixYvZzJkzLf4Mfvzxx8zb25vt2LGDZWRksMcff5y1bdvWqPwDBw5kXbt2ZUePHmUHDx5kkZGR7NlnnzXyfP755ywhIcHs+9T9vjl69Cj3nOF3FuG8mDqPhueZL+zhtJeXnOQkJznJKUwn9T2aBnyfx507dzI2fDhjtcMZxrehQ+/8f8WKO/9PSTHpunXrFm99fT5d9vDt3LmTNxflzTaEXFa+Y2OMv9w197zpdDrW4789GOaDzfljjsNic7a82Yo131m0tJQdscfaYyadhstJFRffeVwsBiQSo9uBv/9GYmIi3N3d0bJlS3z66afw8/PjXnLr1i2MHTsWCoUCLVu2xPLly/HQQw/htddeu2tsnp6eCA4ORrt27fDuu+/Cz88Pe/fu5Z4vLS3FpEmTEBAQAC8vLzz88MPc1U56PvzwQwQGBsLT0xOTJk3C7NmzERcXZ7LsgYGBGDZsGNauXVsvlrVr12LEiBFGZTMVb3h4OIKDgxEcHIyAgIC7llHPxYsXIRKJ8OOPP6Jfv36Qy+Xo2rUrjhw5AplMhv3798PT0xMA8PDDD0MkEmH//v31PPrlfgx57bXX8NBDD3H3dTodVqxYgbZt20Imk6Fr16744YcfuOf1yx39+eefSEhIgFwuR+/evbkrsfTs2rULPXr0gFQqhb+/P5577jnuuaqqKsyaNQutW7eGQqFAz549TcZbF5FIhODgYLRs2RK9e/fGxIkTkZycjPLycu6Yn376CfHx8ZBKpWjXrh0WLFjAzXLSO7788ks89thjkMvliImJwZEjR5CTk4OHHnoIQUFB6N27d72rw1atWoWIiAi4ubkhOjoamzZt4p4bM2YMRo0aZXS8RqOBv78/Nm7cCJlMBp1Oh8WLF5vNKwDs3r0bUVFRkMlk6NevH3eFnSkM66eLiwvGjBljVDevXr2K/fv3Y8yYMfVea64semd2djYeeOABSKVSxMbGGn2u9Fy5cgUjR46Ej48P/Pz8MHz4cJPxmmuXtFotfvjhBwwbNqzec7m5uTh8+DBmz56NqKgo/Pjjj0bPG87uaojk5GQsWrQIy5Ytw5IlS9C7d2+Eh4dj4MCB2LZtG8aPH3/XOG1lwYIFePPNN9G5c2eLjmeM4dNPP8V7772H4cOHo0uXLti4cSOuX7/OLemVlZWFvXv34quvvkLPnj3Rt29ffPbZZ9iyZQuuX7/OuYYNG4aUlBSLr3CMiYmxunyE82GP82yvuuMssZKTnOQkJzmF4ySaIJbMyLg9OxqA2RkZOp3OqmVXG4JPlz18fEJ5sw0hl5Xy5niXOUQiEbdXxspjK1GqLrXodc09b/cCGsiwEMYYVNUqq26lqlKrX2Pqxgw6DBpTnQGdrt5G3vDwqB3IMIg/KSkJQ4cORY8ePZCRkYFVq1ZhzZo1WLhwIXfczJkzcejQIezcuRN79+7FwYMHuenSlqLT6fDdd9+hpKTE6AfOZ555Bjdu3MCvv/6K1NRUxMfHo3///ii+PfiyefNmfPTRR/jkk0+QmpqKsLAwrFq1qsGyT5w4Efv27eOmzAPAhQsX8Pfff2PixIl3jdVkPq3g3XffxaxZs5Ceno6oqCg8++yzqKysNBpI2LZtG/Ly8tC7d2+b3mPx4sXYtGkTVq9ejczMTLz++ut47rnncODAgXqxLFu2DCkpKXBxccGLL77IPffLL7/giSeewNChQ3H8+HH8+eef6N69O/f8tGnTcOTIEWzZsgUnTpzAM888g8GDB3NT2C3hxo0b2L59OyQSCbdvwMGDBzFu3DjMmDEDp0+fxpdffon169fjo48+MnrtwoULMW7cOKSnp6NDhw4YM2YMXn75ZcyZMweHDh0CYwzTpk3jjt++fTtmzJiBN954A6dOncLLL7+MCRMm4K+//gIAjB07Frt27eKWsAKA3377DRUVFXjiiSeg0WiwePFibNy40Wxer1y5gieffBLDhg1Deno6N7Bmjrp16cUXX8R3333HLXW0fv16DB48uN5mig2VRb8c1JNPPgk3NzckJSVh9erVePvtt+u996BBg+Dp6YmDBw/i0KFD8PDwwODBg7llmMzFqefEiRMoKytDQkJCvefWrVuHRx99FN7e3njuueewZs0ao+f1y+bcjc2bN8PDwwP/+te/TD5vuH9M3Tg7duwIDw8Ps7chQ4bc9f2t+bzn5uYiPz8fAwYM4B7z9vZGz549ceTIEQDAkSNH4OPjY5SzAQMGQCwWc8tBALXLUgQFBeHgwYMWvbd+yRKiaWOP82yvuuMssZKTnOQkJzmF4ySaIHfb7BsAbi/dCqDBpaX4WuKET5c9fHxCebMNIZeV8uZ4V0M8Hv04YgNiUV5Vji+OfWHRayhv9qfZ7JHRWCo0FfBY7OGQ91bOUULhpgAAoyvZAdR2Jm6vxQsA8POrnX0RHQ3cXgefMYZLly7hyy+/REBAAD788EP4+vqiQ4cOuH79Ot5++2188MEHUKlU2LBhA7755hv0798fQO0PmK1atbIozrfffhvvvfceqqqquHVXJ02aBAD4559/kJycjBs3bsD99hUbS5cuxY4dO/DDDz/gpZdewmeffYaJEydiwoQJAIC5c+fi999/536Mrld2AIMGDUKrVq2wbt06zJ8/H0DtD8ahoaFcGe4Wr55FixZh+vTpFpVVz6xZs/Doo48CqL3iu2PHjjh79iy6d++OwMDaNfT0aybbQlVVFRYtWoSdO3dy5WnXrh3++ecffPnll3jwwQe5Yz/66CPu/uzZs/Hoo49CrVZDKpXio48+wujRo7FgwQLu+IiICAC1a/6uW7cOly9f5s71rFmzsGfPHqxbt67BjZ/Lysrg4eEBxhj3g/306dOhUCi4nMyePZu70r5du3ZYuHAh3nrrLcybN4/zTJgwASNHjgRQe1569eqF999/H4MGDYJSqcSMGTO4egHU1p0XXniB+0F85syZOHr0KJYuXYp+/fph0KBBUCgU2L59O55//nkAwDfffIPHH38cnp6euHnzJhYtWoQ//vgDvXr1MplX/SyJZcuWAahd0/nkyZP45JNPTOaibv3s1q0b2rVrhx9++AHPP/881q9fj//85z/c+vSWlGXr1q34+++/cebMGfz222/c+Vm0aJHRD/dbt26FTqfDV199xe1/sW7dOvj4+GD//v145JFHzMap59KlS5BIJFy91aPT6bB+/Xp89tlnAIDRo0fjjTfeQG5uLtq2bQvA8oGM7OxstGvXzqIvz7px7t69u8GBCEtmcJgruyn0a5rXHXgKCgrinsvPz4e/v7/R8y4uLvDz8+OO0dOqVSujAdeGuHnzJiIjIy2OlXBO7HGe7VV3nCVWcpKTnOQkp3CcRDPCyhkZhnv7NRY+Xfbw8QnlzTaEXFbKm+NdDSEWiTGn7xw8v/15LD+6HK/d9xrkrvJ7Gpsz5s3e0IwMJ0MkEtUOXmi1tbdTp4DbG9RCLq+dhSES1RvEKCoqQm5uLjp37mw0w6NPnz5QKpW4evUqLly4AI1Gg8TERO55b29vREdHc/cXLVpkdBW04YbZb775JtLT07Fv3z706NEDy5cv5zrEGRkZUCqVaNGihdHrc3NzueVWzp49a/TeAIzuHz582Oi1mzdvhkQiwfjx47F+/XowxqDT6bBhwwZMmDCB25zTHG+++SYOHz6M9PR0pKenY9y4cQCAKVOmGL1PQ3Tp0oX7f8uWLQEARUVFDb7GGnJyclBRUYHhw4cbxbRx48Z6y9SYikV/dVV6enq9gR39D94nT56EVqtFVFSU0XscOHCAew/Dx6dMmcI5PD09kZ6ejpSUFCxbtgxxcXFGsy0yMjLwwQcfGL1+8uTJyMvL4wY+6sau/+FYvwSQSCRCUFAQ1Go1t2RVVlYW+vTpY1SePn36cJtDuri4YOTIkdi8eTMAQKVS4aeffsLYsWMB1M7aqaiowMCBA83mNSsrCz179jR6D/2ghx7D186YMQN1efHFF7Fu3TocOHAAKpUKQ4cOrXdMQ2URiUTIyspCaGio0YBi3TgyMjKQk5MDT09PLh4/Pz+o1ep69UR/3utSWVkJd3f3es/v3bvXKHZ/f38MHDjQaNksc866MHNXcZmgrrNNmzaIjIw0e2vdurXVTj6w1CmTyYzqfEPoZzQRTRt7nGd71R1niZWc5CQnOckpHCfRBOFpaSmFQsFd+NZY+HTZw8cnlDfbEHJZKW+Od92N0Z1GI9wnHEUVRfgq7au7Hk95sz80I8NC5K5yKOco736gnd5bj0Iur90Po+5SUu7uQJ21TQ0HMfR4eno2uG/E3ZgyZQp35TwAox9X/f39uR8Vt23bhs6dOyMhIQGxsbFQKpVo2bKlyX0XDJeTaYj7778f6enp3H39D94vvvgiFi9ejH379kGn0+HKlStGV++bw9/f3+gHdD0ffPABZs2aZVFMhleW63/QdDfsyN0FsVhc78ddw6vO9bNRfvnll3o/1NZ9H1Ox6Ne/MzXiqm/AlEolJBIJUlNT6/0Rox/IMcy7l5eXUfz6waqYmBicP38er7zyCrfHg1KpxIIFC/Dkk0/We3+pwRRkU7HrH1MoFPXKYwljx47Fgw8+iBs3bmDv3r2QyWQYPHiwkceSvDaEubwYxvDWW29h/vz5eP755+HiYl2Ta+mXjFKpRPfu3bmBG0Pq7v1izunv74+KigpUV1cbLQm3Zs0aFBcXG9UhnU6HEydOYMGCBRCLxQgICIBKpYJOpzMaQCwtLQVQOyAKAFFRUfjnn3+g0WjuOiujbpwdO3ZscEbD/fffj19//dUqZ0PoZ1EVFBRwA4P6+/p9e4KDg1FYWGj0upqaGhQXF9ebhVVcXGzxPjymlvcimh72OM/2qjvOEis5yUlOcpJTOE6iCWLubzE3t9oLKRmzaGkp1e1jLN1nryH4dNnDxyeUN9sQclkpb4533Q0XsQve7vM2XvnlFSw5vARTEqbATWL+fSlv9odmZFiISCSCwk1h1Q0aWP0aUzfDK35VSmX9QQy5HOjUiZuFAZgexIiPj0daWprRD+eHDh2Cp6cnQkJCuCVfjh07xj1fVlaGc+fOcff9/PyMroI298Osn58fRo0ahTlz5nDvnZ+fDxcXl3pXUuuXZomOjjZ6bwBG93U6ndHr9JtpR0RE4MEHH8TatWuxbt06DBgwAG3atGn4hOrzadjRuk1gYKDR+1hLZWWlxccGBAQgLy/P6DHDH8djY2Ph7u6O7OzsenkLDQ21+H26dOmCP//80+gxfdm7desGrVaLGzdu1HsP/Y+xho/VXXrIkOnTp2Pr1q3cvirx8fE4e/asySvo7zZjpm6chsTExODQoUNGjx06dAixsbHc/d69eyM0NBRbt27F5s2b8cwzz3A/nrdp0wbu7u64fPmy2bzGxMQgOTnZ6D2OHj1qdN/wdaZ+JPfz88Pjjz+OAwcOGO1ZYmlZVCoVYmJicOXKFaN6UjeO+Ph4ZGdn16u7kZGR3CCCHlP5BMD9OH/aYKm6mzdv4qeffsKWLVu4mUvp6ek4fvw4SkpK8PvvvwMAQkNDUVNTY1R3AXD1ICoqCkDtJuxKpRJffGF6fUn9wIepOHfv3m0UQ93bV1/d/eoIc2U3Rdu2bREcHGz0uSkvL0dSUhI3I6ZXr14oLS1Famoqd4x+QNVwNo9+Zky3bt0seu+67SDRNLHHebZX3XGWWMlJTnKSk5zCcRJNEHMzMiSS2htAMzLsCOXNNoRcVsqb412W8ELcCwj2CMbV8qvYlLGpwWMpb/aHZmTYEWuWUbGJrl1rl5LSLyd1m7KyMvz6668oKSnhHuvSpQtmzpyJ1atX49VXX8W0adNw9uxZzJs3D9OmTYNYLIanpyfGjx+PN998E35+fggMDMS8efMgFoutXpKFMYYZM2agU6dOSElJwYABA9CrVy+MGDEC//73vxEVFYXr169zm1AnJCTg1VdfxeTJk5GQkIDevXtj69atOHHiBNq1a8c5zTFx4kRMnjwZQO0eGdbE6UgefvhhLFmyBBs3bkSvXr3w9ddf49SpU9wPnp6enpg1axbefvttuLq6om/fvigrK8OhQ4fg5eXF7T1xN+bNm4f+/fsjIiICo0ePRk1NDbZv3465c+ciKioKY8eOxbhx47Bs2TJ069YNhYWF+PPPP9GlSxduDxBLaN26NZ544gnMnTsXP//8M+bOnYvHHnsMYWFhePrppyEWi5GRkYFTp07hww8/tMhp6hy9+eabGDlyJLp164YBAwZg165d+PHHH/HHH38YHTdmzBisXr0a586d4zYCB2pnmsyaNQuvv/46dDqdybxOmTIFy5Ytw5tvvolJkyYhNTW1wbplri6tX78eX3zxBVq0aGHy+YbKwhjDgAEDEBUVhfHjx2PJkiUoLy/Hu+++a+QYO3YslixZguHDh+ODDz5ASEgILl26hB9//BFvvfUWQkJC7hpnQEAA4uPj8c8//3CDGps2bUKLFi0wcuTIem3A0KFDsWbNGgwePBgxMTF45JFH8OKLL2LZsmVo164dzp49i9deew2jRo3iZr307NkTb731Ft544w1cu3YNTzzxBFq1aoWcnBysXr0affv25ZboqhunpYOT5rh8+TKuXr2Ky5cvQ6vVcoMukZGR3MyjDh06YPHixXjiiScgEonw2muv4cMPP0T79u3Rtm1bvP/++2jVqhVGjBgBoHYQauDAgZg8eTJWr14NjUaDadOmYfTo0Uaz1Y4ePQp3d/d6S4KZw5qZR4TzYo/zbK+64yyxkpOc5CQnOYXjJJoRLi61Axk1NcYDGWb2pxPyFcZCvmKZ8mYbQi4r5c3xLkuQukjxRq838ObeN7H4n8UYHzceLmLTP6dT3uwPzciwI/bYDd5oBoRYXNthqPMD4/79+/Hoo4/iueee424rVqxA69atsXv3biQnJ6Nr166YMmUKJk6caPSj6H/+8x/06tULjz32GAYMGIA+ffogJibGaBkgS3B1dUVsbCweeeQRzJ07FyKRCLt378YDDzyACRMmICoqCqNHj8alS5e4JaLGjh2LOXPmYNasWYiPj0dubi5eeOEF7r0byudTTz0Fd3d3yOVy7kdGS+PkG2vWmB00aBDef/99vPXWW+jRowdu3brF7dWhZ+HChXjnnXewePFixMTEYPDgwfjll1+4jZYt4aGHHsL333+PnTt3Ii4uDg8//DCOHz/OPb9u3TqMGzcOb7zxBqKjozFixAgcO3YMYWFhFr8HUJvP119/Hb/88guSk5MxaNAg/Pzzz/j999/Ro0cP3HfffVi+fLlVP0qbOkcjRozAihUrsHTpUnTs2BFffvkl1q1bh4ceesjouLFjx+L06dNo3bq10T4Urq6uWLhwId5//32zeQ0LC8O2bduwY8cOdO3aFatXr25w43NzdUkmk5kdxLhbWVxdXSEWi7F9+3ZUVlYiMTERkyZNMtqHBADkcjn+/vtvhIWF4cknn0RMTAwmTpwItVpdb8mrhur8pEmTjJanWrt2Lfejfl2eeuop7Ny5E0VFRXB1dcXWrVvx4IMP4uWXX0bHjh0xffp0DB8+vN5MiU8++QTffPMNkpKSMGjQIHTs2BEzZ85Ely5djAbm+P5szp07F3369MG8efOgVCrRrVs3dOvWDSkpKdwxZ8+eRVlZGXf/rbfewquvvoqXXnoJPXr0gFKpxJ49e4zaww0bNqBDhw7o378/hg4dir59++K///2v0Xt/++23GDt2LOTyhjcG02PpElSEc2OP82yvuuMssZKTnOQkJzmF4ySaIOYuAnRxqb0BFs3IkMlkvG02y6fLHj4+obzZhpDLSnlzvMtSpiRMgb/cH+dLzuObk9+YPY7yZn9EzNGXpN9jysvL4e3tjbKyMkikEngsrr0SVzlHWbsc1G3UajVyc3PRtm1bq3/E11NTU2P1mvh3dVZXw+XEido73brdmcJ5G5VKhTNnznBXM0dERMDX19fmOFUqFVq3bo1ly5Zh4sSJlsfJU9kHDhyI4OBgbNq0yT75JCc5yclRWVmJ6OhobN261eLZA3dz2kpTcRYVFSE6OhopKSlmBx/rft+UlpZyewcZfmeZ2oeFcA5MnUfD88wX9nDay0tOcpKTnOQUppP6Hvzz999/Y8mSJUhNTUVeXh62b9/e4MV3P/74I1atWoX09HRUVVWhY8eOmD9/PgYNGmTxe/J9Hnft2oVhn38O3F5a1oj33gP+7/+A8nKgRw9Av1TZ+vWAiRUE9BcO1V0C1xb4dNnDt2vXLgwbNowXF+XNNoRcVr5jA/jLHeWtPh//8zHm/DkH7f3a4/TU0yZnZVDebMOa7yyakWFH1Go1fzLGAK0WVXfZf0GhUCAiIgJisdiiQQzAOM7jx4/j22+/xfnz55GWloaxY8cCAIYPH25VuLaUvaKiAv/5z3+QmZmJM2fOYN68efjjjz+4q7R5zedtyElOct5BJpNh48aNRnvrNNZpK03FefHiRXzxxRdWzaA6e/ZsY8MinAB7nGd71R1niZWc5CQnOckpHCdxB5VKha5du2LlypUWHf/3339j4MCB2L17N1JTU9GvXz8MGzbMaEa9oNAvLQUAhr9XmJmRIZFIrFrFoCH4dNnDxyeUN9sQclkpb453WcPUHlPhJ/NDdnE2tp7aavIYypv9oT0ynAHGgLNnAaUSlmzL4uPjg86dO9u8NMvSpUtx9uxZuLm5oXv37jh48CC3Ibc90S8/9dFHH0GtViM6Ohrbtm3DgAED7P7eBEHUUnd5LqJxJCQkICEhwdFhEARBEARBEA5iyJAhGDJkiMXHf/rpp0b3Fy1ahJ9++gm7du3i9lJ0CDwtLUUQBOGMeLp74o1eb+Ddfe9i4d8LMbrTaEjEzj8w4GzQQIYdsXVJKiMYq90kS6k0ftzDAxCLwRjjpuAYYs0ghmGc3bp1Q2pqaqNCruu0FJlMVm+z5sY67wY5yUlOcgrNGRUVxbuTEB72OM/2qjvOEis5yUlOcpJTOE6CP3Q6HW7dugU/Pz/HBtLQQIYVMzK0Wi1vIfHpsoePTyhvtiHkslLeHO+ylmmJ07D08FKcvXkW32V+h2c7P2v0POXN/tBAhh3RarWNW4+dMSAry+iqhqqYGLhLpbWDGAAuXbqEoqIihISEIDg42DFxkpOc5CQnOXmjpKTEomUBCeem7nlmjKGmpqZRHcyioiK7bOBmDy85yUlOcpKz8U5XV1delomgvoewWbp0KZRKJUaOHGn2mKqqKlRVVXH3y8vL+Q/E3ECGRHJnRoYFAxnu7u68hcSnyx4+PqG82YaQy0p5c7zLWrzcvTCz10y8/9f7WPj3QozsONJoVgblzf7QQIYd0Wg0tlUUxgCdDjh9GjDojMDDAxrG4C6RgDHGDWIAwLVr1+Dj42PT1cE2x0lOcpKTnOTk3VlYWIh27drx6iSEh+F5rq6uRl5eHioMl2OwgaqqKuTm5vIRnt295CQnOclJzsY7RSIRQkJC4OHh0Sgn9T2EyzfffIMFCxbgp59+QmBgoNnjFi9ejAULFtR7/Ndff4VcLm90HDqdDoWFhQgw8dypM2fQrroacgBapRL6n/SyTpxAzq5d9Y5ntwdERCJRo+Pi02UPn06nwy4TObAFypttCLmsfMcG8Jc7ypt5IrWRUEgUyCrKwpxNc3C/3/12i60p5a0hrPk7mAYy7IhNlcPELAy4uwOxsYBYDFFFRb1BDABo166dzUuc8FmJyUlOcpKTnMJzEsJDf551Oh1yc3MhkUjQqlUruLm52VwHKioqePmx4l54yUlOcpKTnI1zMsZQWFiIq1evon379o2amUF9D2GyZcsWTJo0Cd9///1d942cM2cOZs6cyd0vLy9HaGgohgwZAi8vr0bHsmvXLgS0aGHyuU5xccBffwE3bkBSU8M9HhMZiZhhw+odX11dDQBwc3NrdFx8uuzh27VrF4aZyIEtUN5sQ8hl5Ts2gL/cUd4a5pzvOczbPw+7Vbvx8biPIRaJ7RJbU8ubOayZRUgDGXZEobBka24DTA1iyOVATAxwu3Mpl8vrDWJEREQ0aiqw1XGSk5zkJCc57eZMTEzk3UkID/15rq6uhk6nQ2hoaKN/7LLHni328pKTnOQkJzkb7wwICMDFixeh0WgaNZBBfQ/h8e233+LFF1/Eli1b8Oijj971eHd3d/svG1JnX04OFxfTy06ZWVpKpVIB4OfHND5d9vDxCeXNNoRcVsqb4122Mr3ndPznyH+QWZiJbae34ZmOz9gltqaWNz4QOzqApoy+kliMTndnEMPdHejWzWgQgzGGnJwcXgcxbIqTnOQkJznJaTdnamoq705CeNQ9z2Jx47tk9qiP9vKSk5zkJCc5G+/kayYF9T3si1KpRHp6OtLT0wEAubm5SE9Px+XLlwHUzqYYN24cd/w333yDcePGYdmyZejZsyfy8/ORn5+PsrIyR4R/hxUrAFODXi4ugMFvFBxmBjIUCgVvFwPx6bKHj08ob7Yh5LJS3hzvshUfqQ9m9JwBAPjg7w+gYzoAlLd7AQ1k2BFmbjMs0wcDZ8/euR8bW7tplsEgxqVLl4w6L3wMYlgdJznJSU5yktOuzhqDKflE08Ue59ke9dFeXnKSk5zkJKdwnNT3sC8pKSno1q0bunXrBgCYOXMmunXrhrlz5wIA8vLyuEENAPjvf/+LmpoaTJ06FS1btuRuM2bMcEj8HGFhQFISMGKE8eMuLoCpCzIamJHB1yAfny57+PiE8mYbQi4r5c3xrsbw2n2vwcvdC6dunMKOMzsAUN7uBTSQYUdcXKxYuctwNoZcXq8jcPXqVd5nYuixKk5yCs4pEomwY8cOi10vvPACRowYcdc4n3/+eSxatMhiL9A08mkv5549exAXFwedTseb0xbIKXynn58f705CeNjjPNujPtrLS07+nTt27EBkZCQkEglee+01rF+/Hj4+Po1y8g05LWf//v0QiUQoLS3lzWkJppy29jUbcgK29TXv5mwMQnTed9992LZtG69OU1Dfw7489NBDYIzVu61fvx4AsH79euzfv587fv/+/Q0e73DqzgSyciBDKpXytuwany57+PiE8mYbQi4r5c3xrsbgK/PF9MTpAIAPDtTOyqC82Z9mM5CxcuVKxMbGokePHgBqr4o4duwY9/yxY8dw+vRpVFZWIikpCRkZGdBqtaiuroZSqYRSqYROp0NlZSWUSiUqKyuh0+m456qrq6HRaIyO1T9fcXuDbnPHarVaqKuquFhYdDSUKhWUSiWqqqpQU1MDuVzOrXsaFhYGV1dXbiRNZXDsuHHj8Nhjj0GpVKKmpgZVVVVQKpX1jlWr1dBqtVAqldBoNEbHKpVKs8fqjzc8ljGGNm3aQCQSQSQSQS6Xo3v37vj888+h0Wjq5bCiosJsDs3lu6KiAi4uLvVymJmZyb2vSCSCm5sbIiIisHDhQty6dYvLS718q9VcjgBwz+nzbepYU/k2PFafQ41GA5VKhfXr10MkEiE6OrpeDrds2QKRSIQ2bdpwOdTnxVS+DWM0PLayshIAuDyZynfdOqs/3wDq1Vn9sUePHsXu3bvx4osv1quz69atg0QiwZQpU+rVb/2PJqbyLRKJsGXLFqOybNmyBQ8++CC8vb3h4eGBzp07Y+7cubh8+TKXb32O1Wq1yXxbW2cvX76MCRMmwMvLCz4+PnjhhRdQVlZmdGzdHD7wwANG9UwkEmHixIlGxx49ehT9+/eHj48PfH19MXDgQBw/fpzzPPzww3BxccGaNWtM1m9TbYQ+j4b1sO6x1tZZsVhsMocNtRF3y7dOp7trG2FYZ+sea6qN0Gg0VrcRDbXJWq3WbJvcUBuhz4u5fIvFYqvbiLrHqlQq7v2TkpJQUFCAmzdv4tKlS0hJSWnENx/haEz1PZKSkqDRaFBWVoakpCTk5OSAMcbVG0vacXP1XCKR3LVdMVXP79aumKvnY8eOxeOPP25RPa/brjSm71G3z9GpUyf897//5cpnj77HokWL4Ovry/Ut9DmsrKzEjRs34OXlhRUrVnDxLV26lIvHMF6RSASZTIaQkJAG23GRSIRvv/3Wqr7HSy+9hKeffhpnz57F22+/Xa//UDffjel7GObQmjoLmO97NNSOr169msufWCxGcHAwRo0ahaysLK5u2NqO19TU1DuW776HUqmEi4tLg/mum0O1Wg0ADeZb39fs0KFDvXxv2rQJIpEI4eHhZvNtad8DgNV9D335zPU9jhw5gt27d2P69On1cqjva77yyiv18v3rr79ynyORSITAwEAMHz4cZ8+etVvfIz09HcOHD+c+y0uWLLlrnVUqlTh+/Dj69+8PqVSKkJAQfPLJJ0Y51Gg02LRpE6KioiCVStGpUyds27bNqM6+8cYbePvtt43iNWyTK25fCHfy5EkkJSXhwoULKC0tRVJSEpKSklBSUoILFy4gKSkJycnJAGqXkUpKSkJ2djbKy8up70FYT92BDHPLY5oZyNC3NXzAp8sePj6hvNmGkMtKeXO8q7G83ut1eLp5IqMgA9uztlPe7gWsmVFWVsYAsLKyMqasUjLMB8N8MGWV0ui4yspKdvr0aVZZWWnze926dcvyg2tqGDt2rPZWU2PyEJVKxa5fv96gZvz48Wz48OFWRGllnGZo06YN++CDD1heXh47f/48W7BgAQPAdu/e3Wi3HlNx5ubmMgDsjz/+YHl5eezixYvs66+/ZlKplH311Vc2OfmKc926dUyhUDA/Pz92+PBho2MGDRrEwsLCWJs2baxymgIA2759u8Xx6etIQ86JEyeyl19+2eRz/fv3Z7Nnz2a+vr71Ph+rVq1i3t7eFsX5zjvvMIlEwmbNmsUOHTrEcnNz2e+//86efPJJ9umnn3LH8X2OBg8ezDp37syOHj3KDh48yCIjI9mzzz7b4GsefPBBNnnyZJaXl8fdysrKjGL09fVlL7zwAjtz5gw7deoUe+qpp1hQUBCrrq7mjvv8889ZQkKCxbHas36SUzjOut83R48e5Z4z/M4inBdT51F/nvnob+ixRx1vyGtLn+NuTkuo2+f4+OOPGQC2bds2m53m0MdZUFDAXF1d2ebNm+sds2HDBubu7s5u3rzJxbd8+XKT8ebl5bGcnBx248aNBt/X2u/2vLw8BoDt27ePe2zdunVmv5MtQUht5rp165iXlxfLy8tj169fZ4cOHWJdu3ZliYmJgoqTT+dff/3FALCSkhKzx6xatYq3vmZDcdra12zIaWtfU5+XtLQ0dv36dXbgwAEWHR3NYmNjWY2Zv6Esxdw5Sk5OZrNmzWLffvstCw4ONvp8m6OsrIwFBQWxUaNGsVOnTrFvv/2WyWQy9uWXX3LHHDp0iEkkEvbvf/+bnT59mr333nvM1dWVnTx5kjumpqaGBQUFsZ9//tlknHx9h1Dfo+nB93ncuXPnnTtPP81Y7eLYtbdvv2XM29v4MYCxSZNMum7dusVbO8unyx4+o7w1EsqbbQi5rHzHxhh/uaO8Wc7cfXMZ5oPFroxlpWWllDcbsOY7q9nMyBA0dffHALjpo4bI5XJ4eno26q0OHDiAxMREuLu7o2XLlpg9e7bRmqi3bt3C2LFjoVAo0LJlSyxfvhwPPfQQXnvttbu6PT09ERwcjHbt2mHmzJnw8/PD3r17uedLS0sxadIkBAQEwMvLCw8//DAyMjKMHB9++CECAwPh6emJSZMmYfbs2YiLi7vre7do0QLBwcFo06YNxo4diz59+iAtLY17/tixYxg4cCD8/f3h7e2NBx980Oh5xhjmz5+PsLAwuLu7o1WrVpg+fTr3fFVVFWbNmoXWrVtDoVCgZ8+eRtN/zeHi4oIxY8Zg7dq13GNXr17F/v37MWbMmHrHr1q1ChEREXBzc0N0dDQ2bdpk9Hx2djYeeOABSKVSxMbGGuVXz5UrVzBy5Ej4+PjAz88Pw4cPx8WLF+8aqx6tVosffvgBw4YNq/dcbm4uDh8+jNmzZyMqKgo//vijxV5DkpOTsWjRIixbtgxLlixB7969ER4ejoEDB2Lbtm0YP368Td67kZWVhT179uDzzz9Hz5490bdvX3z22WfYsmULrl+/3uBr5XI5goODuZuXlxf33JkzZ1BSUoIPPvgA0dHR6NixI+bNm4eCggJcunSJO27YsGFISUnB+fPn7VI+giAIIXGv+hxvv/02/Pz8sG/fPu55vvscgYGBGDZsmNH3uZ61a9dixIgRDS7Noo83ODgYQUFBCAgIuGsZ9Vy8eBEikQg//vgj+vXrB7lcjq5du+LIkSMAapcgadmyJQDg4YcfhkgkMtlHqbvcDwC89tpreOihh7j7Op0OixcvRtu2bREQEICuXbvihx9+4J7XL3f0559/IiEhAXK5HL1798bZOv3YXbt2oUePHpBKpfD398cTTzzBPWdrn0okEiE4OBgtW7ZE7969MXHiRCQnJ6O8vJw75qeffkJ8fDykUinatWuHBQsWGNU5kUiEL7/8Eo899hjkcjliYmJw5MgR5OTk4KGHHoJCoUDv3r1x4cIFo/duqH82ZswYjBo1yuh4jUYDf39/bNy4kcvr0qVL0bZtW8hksnp5BYDdu3cjKioKMpkM/fr1s7jvxndfMycnxyn6mgEBAWjZsiUeeOABzJ07F6dPn0ZOTo7FMVhDjx49sGTJEowePRru7u4WvWbz5s2orq7GF198gY4dO2L06NGYPn06/vOf/3DHrFixAoMHD8abb76JmJgYLFy4EPHx8fj888+5YyQSCYYOHcrNaiYIQVB3RoZIVLtUdl3MXPmrn2HHTyj8uezh4xPKm20IuayUN8e7+OD1Xq/DV+qL04Wnse3sNsqbnaGBDEthDFCprLpJtVrzzyuVQHl57a2sDLh5E7i9TBCrrMTlrCxczsoCUypr3/s2jVnP7Nq1axg6dCh69OiBjIwMrFq1CmvWrDHqUM+cOROHDh3Czp07sXfvXhw8eNDoB39L0Ol02L17N0pKSuDm5sY9/swzz+DGjRv49ddfkZqaivj4ePTv3x/FxcUAajv8H330ET755BOkpqYiLCwMq1atsrrsKSkpSE1NRc+ePbnHbt26hfHjx+Off/7B0aNH0b59ewwdOpSbVrVt2zYsX74cX375JbKzs7Fjxw507tyZe/20adNw5MgRbNmyBSdOnMAzzzyDwYMHIzs7u977143zxRdfxHfffcdN/V6/fj0GDx6MoKAgo+O2b9+OGTNm4I033sCpU6fw8ssvY8KECfjrr78glUqh0+nw5JNPws3NDUlJSVi9ejXefvttI4dGo8GgQYPg6emJgwcP4tChQ/Dw8MDgwYNRXV3dYJx6Tpw4gbKyMiQkJNR7bt26dXj00Ufh7e2N5557DmvWrDF63tXV1aSzLps3b4aHhwf+9a9/mXzecE3vunF27NgRHh4eZm9Dhgwx+75HjhyBj48PevfuzT02YMAAiMViJCUl3TVmf39/dOrUCXPmzOHOJwBER0ejRYsWWLNmDaqrq1FZWYk1a9YgJiYG4eHh3HFhYWEICgrCwYMHG3wvc2XnA3IK3xkZGcm7kxAeDZ1nxhhU1Sqrb1qx1qbXGd7qXkQB2FbPzfU5PvzwQ87JV59j27ZtKCkpgVwu5x5vbJ/DVNknTpyIffv2GQ1QX7hwAX///TcmTpxoccy2thvvvvsuZs2ahfT0dERFReHZZ59FTU0NevfujczMTAC1/Zm8vDyj7zlrWLx4MTZu3IjVq1cjIyMDr7/+Op577jkcOHCgXizLli1DSkoKXFxc8OKLL3LP/fLLL3jiiScwdOhQHD9+HH/++ScSExO5slvTpzLHjRs3sH37dkgkEigUCgDAwYMHMW7cOMyYMQOnT5/Gl19+ifXr1+Ojjz4yeu3ChQsxbtw4pKeno0OHDhgzZgxefvllzJkzBykpKWCM4a233uKOb6h/BgBjx47Frl27uKWPAOC3335DRUUFN4CzePFibN26FatXr0ZmZma9vF65cgVPPvkkhg0bhvT0dG5g7W7o+1189DWB2s/Tc889x1tfU0/dOt+YvqYpp0wmAwCz76/vdzZ0O3jwIK/f6UeOHMEDDzxgdOHLoEGDcPbsWZSUlHDHDBgwwOh1gwYN4gYp9SQmJhr1HanvQTicuktJicVWDWQIeakUIS+9QnmzDSGXlfLmeBcf+Eh98GbvNwEAHx36CBXqiru8wnKact5shpc5IE6EzUtLKZX1p0req5vyTmxqtbrB8jW0zMM777zDoqOjmU6n4x5buXIl8/DwYFqtlpWXlzNXV1f2/fffc8+XlpYyuVzOZsyY0eD7tmnThrm5uTGFQsFcXFwYAObn58eys7MZY4wdPHiQeXl51Ys/IiKCm2Lds2dPNnXqVKPn+/Tpw7p27Wq27PqlpWQyGVMoFMzV1ZUBYC+99FKD8Wq1Wubp6cl+/PFHxhhjy5YtY1FRUUbLAOm5dOkSk0gk7Nq1a0aP9+/fn82ZM6fe8fo4DZd0iIuLYxs2bGA6nY5FRESwn376iS1fvtxoun/v3r3Z5MmTjVzPPPMMGzp0KFOr1ey3335jLi4uRnH8+uuvRtP9N23aVO8cV1VVMZlMxn777TfG2J06Yq4ubd++nUkkEiOHPmehoaFsx44djDHGCgsLmZubG7tw4QJ3zH//+1+LlpYaMmQI69Kli8nj6lI3zosXL7Ls7Gyzt6tXr5p1ffTRRywqKqqeMyAggH3xxRdmX/fll1+yPXv2sBMnTrCvv/6atW7dmj3xxBNGx6SmprKIiAgmFouZWCxm0dHR7OLFi/Vc3bp1Y/Pnz7ek6Hf9vNsCOYXnrPt9Y1hvaHmHpoGp86g/z6aWBTHsn9zrW93+EGPm63lj+hyFhYW89zkyMzMZY/z0OUyVvaamhrVu3ZrNmzePe+z9999nYWFhTKvVGsVXd2kpfbz624oVKxoso+F3pr6vY7hkZmZmJgPAsrKyGGOM5efnMwDsr7/+4o6pu7SUqfM1Y8YM9uCDD3Jllcvl3BJF+rJPnDiRW4JRv6zPH3/8wTl++eUXBoCrw7169WJjx441Wa5z585Z1acyLAsAplAomFwuZwAYADZ9+nQuzv79+7NFixYZvW7Tpk2sZcuW3H0A7L333uPuHzlyhAFga9as4R779ttvmVQq5e431D9jjDGNRsP8/f3Zxo0bueefffZZNmrUKMbYnbzu37/fyGGY1zlz5rDY2Fij599+++27Li1l2O9qbF+TMcZ7X1NP3c9iY/qa+jqYn5/PGGPs+vXrrHfv3qx169asqqrKZJ7Ky8sb7DtmZ2eziooKi77T636+zTFw4ED20ksvGTn1n9vTp08zxhhzdXVl33zzjdHrVq5cyQIDA40e++mnn5hYLObaGUMnX0tLUd+j6WHXpaVGjzb+veKHHxiTyer/jjFypElXZWUlL0tq8u2yh4/PJZIob7Yh5LLyHRtj/OWO8mYdt6pusYB/BzDMB1t1dBVPUTX9vOmhpaWaMI0ZPcvKykKvXr2MphL16dMHSqUSV69exYULF6DRaLir5gDA29sb0dHR3P1FixYZXb10+fJl7rk333wT6enp2LdvHxISErB8+XLu6p6MjAwolUq0aNHC6PW5ubncMjtnz541em8ARvf3799v9NrNmzdzz23duhXp6enIyMjAd999h59++snoSraCggJMnjwZ7du3h7e3N7y8vKBUKrlp8M888wwqKyvRrl07TJ48Gdu3b+eWIjh58iS0Wi2ioqKM3v/AgQNc7IaPm5pl8OKLL2LdunU4cOAAVCoVhg4davL89OnTx+ixPn36cBtZZmVlITQ0FK1ateKe79Wrl9HxGRkZyMnJgaenJxePn58f1Gp1veWMzNWlyspKuLu715tytnfvXqPY/f39MXDgQKOlDLRarUlnXZiJK37NUTfONm3aIDIy0uytdevWVjvvxksvvYRBgwahc+fOGDt2LDZu3Ijt27dzOa2srMTLL7+MPn364OjRozh06BA6deqERx99lNuQXY9MJjOazcFnnORsGs78/HzenYTwcKbzbEs9v1ufIzs7m7c+R8+ePbF8+XKEhYUB4KfPcfDgQXh4eHCOzZs3QyKRYPz48Vi/fj0YY9DpdNiwYQMmTJgAsbmNTuvEm56ejkOHDmHcuHEAgClTphjF2BBdunTh/q9fSurGjRsA+GmLcnJyUFFRgYEDBxqVfePGjfX6EA3Fkp6ejv79+5t8j4yMDKv6VFOmTOFe6+npifT0dKSkpGDZsmWIj4/HRx99xJU9IyMDH3zwgdHrJ0+ejLy8PKPvXcPY9TMWDGfhBgUFQa1Wc0tWNdQ/A2qXdho5ciTXL1WpVPjpp58wduxYo7w++uijRrEZ5jUrK8toJjFQv49nKi+G/a7G9jX1z4eEhPDW19RTt342pq+pJyIiAgqFAq1atYJKpcK2bduMZoIb4unp2WDfMTIyEjKZTLD9BJlMBp1Oh6qqKt6cdXGm7yRCAJiakWHq77sG/t6s+zeSrfDpsoePTyhvtiHkslLeHO/iCw83D8zpOwdA7ayMqpoqXrxNPW+24OLoAJwGubx2OSgrUCqV9f8oZQzIzAT0U587dwbEYjAAl69cwc3bSx4AQNu2beHr61v73gJhypQpGDlyJHff8A8df39/7o+BTZs24b777kNCQgJiY2OhVCrRsmVLk2sgGy4j1BDx8fFIT0/n7gcFBeHmzZsAgNDQUG7QJCYmBufPn8f777+P+fPnQyqVYvz48bh58yZWrFiBNm3awN3dHb169eKmoIeGhuLs2bP4448/sHfvXvzrX//CkiVLcODAASiVSkgkEqSmpkIikRjFpD+/hnHVPQaoXXbgrbfewvz58/H888/DxcU+Hz2lUonu3bsbDfLosXQ9bn9/f1RUVKC6utroD8I1a9aguLiYm74P1C5BcOLECSxYsABisRienp5QqVTQ6XRGP+qUlpYCqP2RCgCioqLwzz//QKPRWLwclZ6OHTsaLetRl/vvvx+//vqryeeC/5+98w6L4urC+Lu7LLAsoCAiithQEBuKioIFC0ajsSZWPsWusdeosYAlajTYEktijSbGGlvsDaNoDBZUAmJDRcUKUpay7O79/hh22Aq7y6yseH/Psw+7M3feOffMnZnL3LnnuLmxD1qUyGQypKSkwM3NzWAblA8bHjx4AE9PT+zcuRNPnjzB1atX2Xrv3LkTTk5OOHToEPr168dum5KSYlRsdAqF8ulhJ7RD5izj+hwAkCnJhL248IfhhuzbUjC0z7F3717Ur18fderUQZMmTTjpczRp0gQxMTGQSCQQi8XsA++hQ4diyZIlOHfuHBQKBZKSkjBkyJAi9ZT2Aur9wwULFmDatGkG2aR6v1Q+AFboCuWhBz6fr/UigeoDUWVopKNHj8Ld3Z2tOwCtvACF2aLaT9BEIpEY1adSDcvD5/O1+npff/01GxIsMzMT8+fPR69evbT2qxqKR5ftxfVtSEgIgoKC8Pr1a5w+fRoikQidOnVi7QKAffv2aYXvMTTfAqDfL6o2fAp9TSUnT56Em5sbm+emMH7//XeMGjWq0DLHjx9Ho0aNDLLfENzc3PDq1Su1Zcrfyj6nvjKafdKUlBSIxeJCzy0K5YOiGWOdzwd0vdCmZyBDbGenrWEiyvsUV3CtxyVc2kb9Zhl61G8lr8Ulo5uMxg+Xf8CzjGfYdGMTxvqPLbbmp+A3Y6EDGYbC4wFGHnS1GzQhTNzIuDhAIABEImaAokwZEABPnjzB2+xsZjmYt4ycnJy0NYvR8Hx8fLB//34QQth/0qKiouDg4IDKlSvDyckJQqEQ0dHR7FuNaWlpuHfvHlq3bg0AcHZ2LjSZpRJvb2/07dsXs2bNYhMvvnz5ElZWVmo5AzS3iY6OZt9SBJgk3UpcXFy0/kFSDmRoIhAIIJPJIJVKYWtri6ioKKxbt459wyspKQlv375V++dJJBKha9eu6Nq1K8aOHYvatWvjzp07aNSoEeRyOV6/fo1WrVrp3J/qP6a6Zhs4OzujW7du2LNnDzZs2KBTw8fHB1FRUWqJrqOiolCnTh2IxWL4+PggKSkJycnJ7NuP//zzj5qGn58fdu/eDVdXV53/5Kqiry0pE53GxcWx39+9e4dDhw5h165dqFu3LltWLpejZcuWOHXqFDp16gRfX1/IZDLExMTAz8+PLaeMee7l5QWASYy5Zs0arFu3DhMnTtSy4f379+zDJk07jx07VuibaIX9kxcQEID379/j7t27bFxm5cMozTchC0P5MEF5HLKysiAQCNTeLOTz+eDxeGoPQpRvKxr6j7I5bjRU0/I1Nd8Sp5ROCjvOPB4PYmvj25ad0M4sCdxMaedF9TnKli3LWZ/Dw8MDffv2xcKFCznrc4hEItSsWVPNfoDpnwUFBWHLli0ghCA4OBhVq1Y1yjeq/nR1dYWrq6tR2xelqY/y5csjNjZWbVlMTAz7EL9OnTqwsbHB06dPERQUpFV3Q2nQoAHOnj2rc4CnefPmRvWpCmPmzJnw9PTEpEmT0LhxY/j5+SEhIYHzWP+F9c+UBAYGwsPDA7t378bx48fRu3dvLb++fv2aHdzQtY/Dhw+rLdPs4+mql+pASHH7msr1z54946yvqUSzfRanr6mkTp06Ov9X0kW3bt2K7Oe5u7tzmnsiICAAs2fPVvtf4/Tp0/D29mbtDggIwNmzZzFp0iS1MpqzYGJjY9X6jrTvQSlxipPse9EiWG3YgPQTJ2Bdr16xTZFIJACgd0ZWSetxCZe2Ub9Zhh71W8lrcYlIKMLkJpMxPXI6Fl1chCGNhhT7JbFPwW/GQgcyzEh2djaTeJIQICFBfUaHjQ3g41MwiPH2LbtK3yCGmmYhpKWlqb21BQDlypXDmDFjsGrVKowfPx7jxo1DQkICwsLCMH78ePZt+tDQUEyfPh3Ozs5wdXVFWFgY+0DW2LpPnDgR9erVw7Vr1xAcHIyAgAD06NEDy5Ytg5eXF168eMEmhGzSpAnGjx+PESNGoEmTJggMDMTu3btx+/Zt1KhRo8i6v3v3Di9fvoRMJsOdO3ewevVqtG3blv0Hq1atWtixYweaNGmC9PR0TJ8+XW0K+bZt2yCXy9GsWTPY2dnht99+g0gkQtWqVVGuXDmEhIRg0KBBiIiIQKNGjfDmzRucPXsWDRo0QJcuXQw6Rtu2bcO6detQrlw5nXWYPn06+vTpg0aNGiE4OBhHjhzBn3/+iTNnziA7OxvBwcHw8vJCaGgoli9fjvT0dMyePVtNIyQkBMuXL0f37t2xYMECVK5cGU+ePMGff/6Jb775BpUrVy7SzvLly8PPzw+XLl1i/7ncsWMHypUrhz59+mi1hc6dO2Pz5s3o1KkTatSogc8++wxDhw5FREQEatSogYSEBEyaNAl9+/Zlwz41a9YM33zzDaZOnYrnz5+jZ8+eqFSpEh48eIANGzagZcuW7ACHpp3GPjBSxcfHB506dcLw4cPxyy+/IC8vD+PGjUO/fv3YN32fP3+O9u3bY/v27fD398fDhw+xc+dOdO7cGeXKlcPt27cxefJktG7dmg1P0aFDB0yfPh1jx47F+PHjoVAosHTpUlhZWaFt27bs/v/55x92NpAhGHK+GwvVtHzNmJgYTt8KpVgm5jjO5miPReka2+eYMmUK+Hw+rKysOOtzAOC8z1FY3YcNG4YRI0YAYO7txmKua1FRtGvXDsuXL8f27dsREBCA3377Te0BqYODA6ZNm4bJkydDoVCgcePGkEqliIqKgqOjo9rD78IICwtD+/bt4enpiX79+kEmk+HYsWOYMWMGPDw8jOpTFYaHhwd69uyJOXPm4Pjx45g3bx6++OILVKlSBV999RX4fD5u3bqF2NhYNsm8KRTWP1NlwIAB2LBhA+7du8cmzwYK/DplyhQQQtCyZUukpaWp+XX06NGIiIjA9OnTMXz4cFy/ft2gtqWZ3Lo4fU0ACA4ORq1atTjrayrRbPPF6Wuqaho6kOHg4FDkrA2AeTFF17kplUoRFxfHfn/+/DliYmJgb2/PDjD99NNPOHDgAM6ePQuAaQ/z58/H4MGDMXv2bMTGxmL16tVYuXIlqztx4kQEBQUhIiICXbp0wa5du3Dt2jX88ssvavu/ePEiPvvsM7W6074HpUTRfHHPmGTfBw+C//w5xP/9B3AwkGHJb41zjSW/mf2p+I1rPeq3ktfimlFNR+Gnmz/hSdoTrI9ej6mBU4ul96n4zSg4ycrxEWFysm8TyMjIYL7IZIRERxd8/vuPEIWCKBQKkpiYSKKjo9lPSkqKYZp6CA0NZRMgqn6GDRtGCCEkMjKSNG3alFhbWxM3NzcyY8YMtSSC6enpZMCAAcTOzo64ubmRFStWEH9/fzJz5sxC96uZ+E5pZ8eOHcnnn3/Oao8fP55UqlSJCIVC4uHhQUJCQsjTp0/Z7RYsWEBcXFyIvb09GTp0KJkwYQJp3ry53rorE2AqPwKBgFSuXJmMGDGCvH79mi1348YN0qRJE2Jra0tq1apF9u7dS6pWrUqWLl1KCGGSDjZr1ow4OjoSsVhMmjdvrpbIUiqVknnz5pFq1aoRoVBIKlasSHr27Elu376tZZPSTs0km5poJmAkhJB169aRGjVqEKFQSLy8vNjEkUrNhIQE0rJlS2JtbU28vLzIiRMn1BIwEkJIcnIyGTRoEHFxcSE2NjakRo0aZMSIEWzSHGUCxsLa0rp161i/E0JI/fr1yZgxY3SW3b17N7G2tiZv3rwhGRkZJDU1lUyYMIF4enoSkUhEatWqRb755hud+9u9ezdp3bo1cXBwIGKxmDRo0IAsWLBArU0W1eaN5d27d6R3797E3t6eODo6kiFDhqjtQ9mmlAlTnz59Slq3bk2cnZ2JjY0NqVmzJpk+fbpWEqJDhw6RFi1akDJlyhAnJyfSrl07cuXKFbUyI0eOJKNGjTLYVq7rTjUtU1PzfvPPP/+w62jCzdKBruOoPM5cJWolxDxtvDBdU/oceXl5rCZXfQ4lwcHBnPU5Cqt7VlYWKVOmDHF2dtaZHFhXsm9dfaTCUL23K+9LN2/eZNenpqaq3auSkpKKTPZNCCHz5s0jFSpUIGXKlCGTJ08m48aNY5N9E0KIQqEgq1atIt7e3kQoFJLy5cuTjh07kgsXLhBCChItq96nb968SQCQxMREdtn+/ftJw4YNibW1NXFxcSG9evVi625Mn6qwuhBSkKz76tWrhBBCTpw4QQIDA4lIJCKOjo7E39+f/PLLLzr9qs+3uuqor3+mSlxcHAFAqlatqpXEWqFQkO+//16vXwkh5MiRI6RmzZrExsaGtGrVimzZsqXIZN/r16/nrK+p5MaNG5z1NZXoavOm9jWVxycpKUlvvU1F37mp+f+G8qN67oSFhWn5+tatWyQgIIDY2NgQd3d39v8OVfbs2UO8vLyItbU1qVu3Ljl69Kja+mfPnhGhUKhWX1U7ubqH0L5H6cOsyb4HDFBP6v3XX9qJvgFCWrXSFvLxIQQgGSrX5uKQkpJS5DOUktTjMmk1l7ZRv1mGHte2EcKd76jfTCMlJYWsubiGIBzEZZkLSc9JL7bep+A3Y+5ZPEKMyLpbCkhPT0eZMmWQlpYGga0A9kuYeLyZszLVwjjk5OQgMTER1atXN3macU5ODrOtXA7cvMks9PUFrKwAHg8ymQx3795FTk4OgMJnYmhpckhhmhKJBO7u7oiIiMCwYcM40TSGDh06wM3NDTt27Pjgdf+UNbOzs+Ht7Y3du3cbPHugKE1TKS2ab9++hbe3N65du4bq1atzomkKVNPyNDXvNwkJCWzCY9V7lqEhPCiWh67jqDzOXPQ3lJijjZtLV5emqX2OwjSNQbXPwZWmLqgm1aSapvc1C9MsLpaoOWPGDKSmpqrN0lDV5OoeQvsepQ+uj+ORI0fQtWtX5kf//sCuXQUrjx0D8kM4q9G8OXDlivqyatWAJ08gXb8e1qNHF9su5YxErnLIcK2n5rdiwqVt1G+Woce1bQB3vqN+M43s7GzIFDL4bfHDg5QHWNR2EWa3nl30hoXoAaXfb8bcs/iFrqUUC51JjPl8NqaklZUVvL29IRKJDBrE0KtZTFQ1b968iT/++AMPHz7EjRs3EBISAgDo3r27yZqGkpWVhRUrVuC///7D3bt3ERYWhjNnzrChDMxdd6pZgEgkwvbt29VCnhVX01RKi+bjx4+xbt06gwcxDNE0Bapp+Zq6wnJQSh/mOM7maI/m0hUKhZz1OVQ1DaWoPocpmoZCNakm1TS9r1mYZnGxRE1XV1csXLiQU01d0L4HxSh0hZbSha7QUllZAAB5fqz24pKXl1do/sSS1uMSLm2jfrMMPeq3ktfimry8PBA5wfw28wEAP1z5Ae9z3hdL71PwmzHQgQxzQQhysrKY2Rj5MVV1IRQKjUpWZ0gMZGPR1Pzhhx/g6+uL4OBgSCQSXLx4ES4uLsXSNAQej4djx46hdevWaNy4MY4cOYL9+/cjODjYZM2ioJr6adOmjdEjq6Wl7ubQbNKkCfr27cuppilQTcvX1EzGSymdmOM4m6M9mktXqclFn0NT0xCK6nOYomkoVJNqUk0GU/qaRWkWB0vUnDp1KipUqMCppi5o34NiFJr5MEwYyOBp5PgxFR6PZ1JurQ+lxyVc2kb9Zhl61G8lr8U1Stv61u2LuuXr4n3OeyyPWl5sPS5t+9ihyb7NQX5yb7Fqcm8ARCTCqzdvUL58eQgEAna5JTWkRo0a4fr16yWyb5FIpJU4kUKhUCgUSumE9jkoFAqFQvkI0ZyRoe95huZABiHsQAafo4EM1ecqlqjHJVzaRv1mGXrUbyWvxTVK2wR8ARa2XYhee3ph1dVVGOc/DhUdKpqsx6VtHzt0RoY5UCgAHYMYT+zs8OzZM9y/fx9yudwkaRsbGy4spJpUk2pSTappoZo1atTgXJNieZjjOJujPZpLl2pSTapJNamm5WjSvgfFKEydkZGbyw6CKDgKLSWVSiHlaFDEHHpcwqVt1G+WoUf9VvJaXKNqW4/aPdC8cnNk5WVh4d8Li9iyaD0ubfuYoQMZXEOIeigpX1+QRo3wxM4Ob9+9AwBkZmZCYuKN2xy52akm1aSaVJNqWo5mTk4O55oUy8Mcx9kc7dFculSTalJNqkk1LUeT9j0oRqHaBj09gRYtdJfTHMjIn40BAFYmvtipiUgk4jRxLdd6XMKlbdRvlqFH/VbyWlyjahuPx8PS9ksBABtvbMSDlAfF0uPSto8ZOpDBBYQwuTDkciA2lnnTAIDc1hbEygpPkpLYQQwA8PT0LDILuz7MMXpGNakm1aSaVNNyNF+8eMG5JsXyMMdxNtcbNh/LuUM1qSbVpJpU0zRo34NiFKoDGQkJgL5ZQoUMZMg0IliYSlZWFrJUdC1Nj0u4tI36zTL0qN9KXotrNG0LqhaEz2t+DplChjnn5hRbj0vbPlZojozikp8PQzOUFGxskF2tGt4+eYK3b9+yiz09PQ1O7E2hUCgUCoVCoVAoFAqFYjGoDmQUFnO9kIEMoUzGiSlisZgTHXPpcQmXtlG/WYYe9VvJa3GNLtuWtF+CEw9OYPd/uzE9cDoaV2pcLD0ubfsYoTMyiouOfBiwswOpVw9v3rzhfBDDHA2PalJNqkk1qablaDZubHjHhvLxYo7jbK7O6cdy7lBNqkk1qSbVNA3a96AYhWaODH0UNiODoxwZEonE5LDdH0KPS7i0jfrNMvSo30pei2t02ebr5osB9QcAAGadnVVsPS5t+xihAxlc4usLNGoE4uODJ0+e4J1GOCkuZmJkZ2cXW4NqUk2qSTWppuVq/vfff5xrUiwPcxxnc7RHc+lSTapJNakm1bQcTdr3oBiFroEMXQNsheXI4GhGhp2dHezs7DjRMocel3BpG/WbZehRv5W8Ftfos21h24UQ8oU4/eg0zj46W2w9Lm372KChpbiEzwcEArx+9cps4aQUhr79UEKaPB4PBw4cQHBwMGeaSriwU2lfjx49ONPURKFQIDIyEm3btkVqairKli0LADh48CCmTZuGxMREjB8/Hg0bNsSkSZPw/v17gzTNYSfVpJpU0/I0acLNTwNzHGdztEdz6VLNj1NTsx9VFIMHD8b79+9x8OBBvZoAMHDgQPj4+ODbb7/lxM7iYmmaUqkUXl5e2LdvH5o0acKJpj6o5qepSfsepRflwBePx4NAIIBUKoVIJEJWVhbEYjEkEgns7OyQnZ0Na2tryOVyEEIgFAqRk5PDliGEIDU1FSKRCAKpFMJ8/fT0dAiFQuQdPgzH9u3V9k3y8pCelgaBMvzUmzewz18ny8xEemoqq29ra4u8vDzw+XzweDzk5eXB1tYW2dnZbBnNsjweDxKJBHl5eXB1dTW6Tsq/IpEIOTk5EAqFSEtLg0KhQLly5fSWzc3NZeskl8thY2Oj105CCDIzM42qk77jJJPJkJOTg3LlyhlVJ0IIFAqFWtlXr15BJBLBysrK6DrpOk6vX79m9Yypk77jRAiBVCo1qk76jlNGRgbkcjlcXFyMqpO+sikpKeDxeChbtqzJ55Pyb15eHnJzc+Hs7GxUnQo7ToQQZGdnm3Q+qR4n1TZi6vmkWqc3b95otRFT215GRgZkMhnKly9v8vmkq07Z2dkmnU+qZaVSKfLy8tjngMo6lUVZjGg0Auuur8OM0zNwqvcpiESiIo+TTCZDdnY2ypcvb/L5pO+8N+V80jxOyntDca/lxuTu+GQGMtauXYu1a9dCLpcDAK5duwa+TcGElOjoaLg6uaJ69eq4ffs2AGbarlQqhSz/bQE7Ozvk5uZCLpdDIBAwBy4rC8p3D/JkMuRmZ8POzg6Ojo5IT0+Hu7s7bGxsQAhhp/BYW1uDx+MhNz8puLLxymQy8Pl8iEQitqxQKIRAIGA7l3w+Hzk5OZDJZODxeGodC6FQiBEjRmDHjh0AACsrK7i7u6NHjx6YO3cuypUrx5a1srKCUChEdnY2FAoFZDIZ5HI58vLfmrC3t9dZFgBsbGygUCjYsmKxmNUBmM61QqFAZmYmW3dlUjo7Ozvk5ORAoVCwPlQ2WGtrawBQK6v0N5/Ph0AgQGZ+GC9dPnz69Cm+//57nDx5Ei9evED58uVRv359TJgwAcHBwWxZhULB+lBps1JX09+qx0aXv1XL2traQi6XQ6FQwNfXF8nJybCyskJmZiasrKwwatQohISE4Ouvv4aLiwt4PB6CgoKQmZmp5kNd/la1UbWspg91+VuzzSrLKi8qSr9o+tvW1lbt2BjSZhUKBXJzc8Hn83WWVfpQn79tbW0hk8nUyirbkpWVFaysrLT8bUqbFQgEyMrK0utvQ9usalllu9fnb00favpb9bxXllXW3ZhrRFFtls/ns/5X9aFmWU2/FOZvgLmZGXKNEAgEsLa2Nsjf2dnZRl0jimqzyn8kdPnQ1DZb1DVZ1zVC0985OTnIy8tDZmYmbt26hYyMDLx79w6ZmZl4+PAhKB8vuvoeYrEYfn5+yMnJwdWrVyEWi8Hn89mOqjHXcc12zufzkZ2dXeh1hcu+x8iRI5GRkYE///yzyHbOZd+jbt26ePr0KVuPGjVqYMKECejXr59Z+x4vXryAt7c3e3yFQiE8PDwQEhKCGTNmwM7OzqDrijn6Hjt27MCYMWNQu3ZtXLt2Tc2HO3fuxKBBg1C1alUkJCTovDYb2vcAgNzcXCgUCoP6Hsp/opQ6uvoe0dHROHr0KCIiItR0ra2tsXv3bgwePBjDhg3D+vXr1drs1atX0a5dO/Z4uLq6onnz5li0aBHq1Kljtr7Hnj17EB4ejqdPn6JWrVqYP38+PvvsM71t9ty5c+jcuTM0efbsGcqUKQMA+P7777Fo0SK19V5eXrh+/TrbZsePH49p06bh9OnTtO9B+x7sNVlp1507d6BQKFC+fHk4OzsjISGBbUepqal48+YNeDwe/P39cf36dchkMjg7O6NChQqIj4+nfY9ShGbfwyyo5sjIR96okXY5jVkXPJUHVXyOktYLhcKiCxmpZ64XQ4qLUCjk7LgKhUJYW1tzVleu9bhEeb3lUo/H43GmZYk+Ayy7jXB5DLhG2W/QxawWs7D99nZcf3kdhx4cQr/6/QzSk8m4mcFmyeepUZBPjLS0NAKApKWlkczcTIJwEISDZOZmqpXLzs4mcXFxJDs7u3BBmYyQ6GjmI5Oxi+VyOXn//j3n9svl8kLXh4aGkk6dOpHk5GTy9OlTcuDAAeLo6Ei++eYbkzWNAQA5cOAAp5pKCtNMTEwklSpVInXq1CH79u0jCQkJJDY2lkRERBBvb28t+wzR5NLOjIwMAoCcO3eOM01CCJFKpSbpFaZZHKgm1aSaxqN5v8nKymLXqd6zKB8vuo6j8jgb3N8wAHO08cJ0Q0NDSffu3TnVNISqVauSBQsWkOTkZPLw4UOydOlSAoD89ddfJmvqQ9XOxMREAoCcOXOGJCcnk8ePH5PffvuN2Nrakk2bNpmkyRWbN28mYrGYODs7k8uXL6ut69ixI6lSpQqpWrWqUZq67NTsRxWFZhvRpTls2DAyatQondu3b9+ezJw5kzg5OWmdI+fPnycASHx8PHnx4gW5cOEC8fb2JnXq1CEylT65Keg7RlFRUUQgEJBly5aRuLg4MmfOHCIUCsmdO3f0aqnamZyczH5U9xEWFkbq1q2rtv7NmzdqOikpKcTa2prExsYWaWdxoJoflyZX9xDa9yh9cH0cDx8+XPCjUydCmOEM9ULKZaof1XPgjz/Y5XmBgZzYlZ6eTtLT0znRMoeemt+KCZe2Ub9Zhh7XthHCne+o30yjKNvCzocRhIPUWlOLSGVFP8/7VPxmzD2L5sgwFUIAuRxQKEAAaER/ZN/i4xpDptvY2NjAzc0NHh4e6NGjB4KDg3H69Gl2/bt379C/f3+4u7vDzs4O9evXxx9//KGm0aZNG0yYMAHffPMNnJ2d4ebmhvDwcLUy9+/fR+vWrWFra4s6deqo7UNp5507d9CuXTuIRCKUK1cOI0eOZN8uApiQAz169MDixYtRoUIFlC1bFgsWLIBMJsP06dPh7OyMypUrY+vWrYXWfcyYMeDxePj333/x5ZdfwsvLC3Xr1sWUKVPwzz//6N1u6tSp8PLygp2dHWrUqIG5c+eyb3IBwK1bt9C2bVs4ODjA0dERjRs3xrVr1wAAT548QdeuXeHk5ASxWIy6devi2LFjyMrKQmRkJHg8Ht6/f4/IyEg4ODgAANq1awcej4fIyEhs27aNnW6m5NChQ/Dz84OtrS1q1KiB+fPnQyaTqc2iWL9+Pbp16waxWIzvvvtOb92KwpipW1STalLND6epnBVIKd2Y4ziboz0WR/fChQvw9/eHjY0NKlasiJkzZ7JvFGVlZSEjIwMhISEQi8WoWLEiVq5ciTZt2mDSpElFajs4OMDNzQ01atTAjBkz4OzsjOPHj7Pr379/j+HDh6N8+fJwdHREu3btcOvWLTWNRYsWwdXVFQ4ODhg+fDhmzpyJhg0bFln3cuXKwc3NDVWrVkVISAhatGiBGzdusOujo6PRoUMHuLi4oEyZMggKClJbL5FIEB4ejipVqsDGxgaVKlXChAkT2PW5ubmYNm0a3N3dIRaL0axZM0RGRhbqD6lUCisrKwwYMABbtmxhlz979gyRkZEYMGCA1jbr16+Hp6cnrK2t4e3tzc7oVXL79m29/TwlSUlJ6NOnD8qWLQtnZ2d0794djx8/1munpj/lcjn27duHrl27apVNTEzE5cuXMXPmTHh5eeHPP//UqWlvb4+KFSuidevWmDdvHuLi4vDgwQO9NhiCvja/evVqdOrUCdOnT4ePjw8WLlwIPz8//PTTT0Vq2tvbw83Njf1ovh1qZWWltt7FxUVtvZOTE1q0aIFdu3YVaWdxoJqfpibte1CMwpi3eVXzZKgkmeUpw5m9eAH8+6/JphBC2FlaXMC1HpdwaRv1m2XoUb+VvBbXFGXb1ICpKG9XHvdT7mPLzS16yxmqx6VtHwt0IMMUCAHi44GbN0Fu3cITAHcB5HI0PZJLYmNjcfnyZbXpTTk5OWjcuDGOHj2K2NhYDBkyBAMHDsS/Gh2IX3/9FWKxGFevXsWyZcuwYMEC9p9YhUKBXr16wdraGlevXsWGDRswY8YMte0lEgk6duwIJycnREdHY+/evThz5gzGjRunVu7cuXN48eIF/v77b6xYsQJhYWH44osv4OTkhKtXr2L06NEYNWoUnj9/rrOOKSkpOHHiBMaOHQuxjiRjmoMFqjg4OGDbtm2Ii4vD6tWrsXHjRqxcuZJdHxISgsqVKyM6OhrXr1/HzJkz2emrY8eORW5uLv7++2/cuXMH33//Pezt7bX2ERgYyE7v3r9/P5KTkxEYGKhV7uLFixg0aBAmTpyIuLg4/Pzzz9i2bZvWYEV4eDh69uyJO3fuYOjQoXrrRqFQKJSPFEKYf/ZL4sNR5/b58+fo3LkzmjZtilu3bmH9+vXYvHmzWvicKVOmICoqCocPH8bp06dx8eJFtQf+hqBQKLB//36kpqaq9XV69+6N169f4/jx47h+/Tr8/PzQvn17pKSkAAB+//13fPfdd/j+++9x/fp1VKlSBevXrze6nteuXcP169fRrFkzdllGRgZCQ0Nx6dIl/PPPP6hVqxY6d+6MjIwMAMxLCytXrsTPP/+M+/fv4+DBg6hfvz67/bhx43DlyhXs2rULt2/fRu/evdGpUyfcv3+/SHuGDh2KPXv2sA86t23bhk6dOqFChQpq5Q4cOICJEydi6tSpiI2NxahRozBkyBCcP3+e9WtISEih/by8vDx07NgRDg4OuHjxIqKiomBvb49OnTqx4W6K4vbt20hLS1PL+6Bk69at6NKlC8qUKYP//e9/2Lx5c5F6IpEIAPTu//fff4e9vX2hn4sXL+rVv3LlilYeuI4dO+LKlStF2taiRQtUrFgRHTp0QFRUlNb6+/fvo1KlSqhRowZCQkLY8Gmq+Pv7F2ofhUKhfBCM6SuoDmSoDMLxlNdpd3egWTMgJsYkU4RCIafhpbjW4xIubaN+sww96reS1+KaomxzsHHAnNZzAADhF8KRKc3UW9YQPS5t+2jgZA7IR4TJoaUUCkJkMhKxfDlxd3VlP26ursRV5ePu7k7c3d1J165dtcL+dO3alV1f2CciIkKv/UWFEgoNDSUCgYCIxWJiY2NDABA+n0/27dtXqGaXLl3I1KlT2WVBQUGkZcuWauWaNm1KZsyYQQgh5OTJk8TKyoo8f/6cXX/8+HE25IBUKiW//PILcXJyIpmZBb49evQo4fP55OXLl6y9VatWVZsi7e3tTVq1asX+lslkRCwWkx07dui0/+rVqwQA+fPPPwv1DSHaIRE0/bl8+XLSuHFj9reDgwPZtm2bTq369euT8PBwreVSqZQNI5CamkoIISQ1NZUAIOfPn2fLbd26lZQpU4b93b59e7J48WI1rR07dpCKFSuydgIgkyZNKrKehlCcsFRUk2pSTe40Ne83ycnJ7Doa3qF0oOs4Ko+zzrAgmZm6wzN8iE9mpqb5ett5YaGlvv32W+Lt7U0UCgW7bO3atcTe3p7I5XLy7t07IhQKyd69e9n179+/J3Z2dmTixImF+rNq1arE2tqaiMViYmVlRQAQZ2dnEhcXRwgh5OLFi8TR0ZHk5OSobefp6Ul+/vlnQgghzZo1I2PHjlVb36JFC+Lr66u37srQUiKRiIjFYiIUCgkAMnLkyELtlcvlxMHBgRw5coQQQsiyZcuIl5eXTr8+efKECAQCtf4VIUwfYdasWXr3sWnTJrZP0bBhQ/Lrr78ShUJBPD09yaFDh8jKlSvVQksFBgaSESNGqGn07t2bdO7cmRBSdD+PEKaPonmMc3NziUgkIidPniSEaLcRzTofOHCACAQCNQ1CGJ95eHiQgwcPEkIIefPmDbG2tiaPHj1iyyj7Wq9fvyaEEPLixQsSGBhI3N3dSW5urk4/paenk/v37xf6ycrK0tvmhUIh2blzp9qytWvXEldXV53lCSHk7t27ZMOGDeSff/4hUVFRZMiQIcTKyopcv36dLXPs2DGyZ88ecuvWLXLixAkSEBBAqlSpojX9f/Xq1aRatWrsb0u9r1HND6fJVWgp2vcofZg1tFT79oaHlkpJKVi/dCm7XObpqb7Njz+aZFdKSgpJUd1HMeFaj8sQSVzaRv1mGXpc20YId76jfjMNQ2zLleUSz9WeBOEg887NK7Yel7YZS0mElvpkkn0XC0KAhAQgMxPp9+7h+evXRW7i4eGhNWXnzZs3emcVqJKenl6IKUW//dC2bVusX78eEokEK1euhJWVFb788kt2vVwux+LFi7Fnzx48f/4cUqkUubm5sLOzU9Np0KCB2u+KFSvidX7d4+Pj4eHhgUqVKrHrAwIC1OyMj4+Hr6+v2iyJFi1aQKFQICEhgX07sG7dumrT6ytUqIB69eqxvwUCAcqVK8fu2xSf6GPPnj1Yt24dHj58iMzMTMhkMjg6OrLrp0yZguHDh2PHjh0IDg5G79694enpCQCYMGECvv76a5w6dQrBwcH48ssv0aBBA5PtuXXrFqKiotRmYMjlcuTk5EAikbAzS3S9tWgKxfEb1aSaVNN8mmZNzkixGD6m42xKO4+Pj0dAQIBaIr4WLVogMzMTz549w+vXr5GXlwd/f392fZkyZdSSaS9evBiLFy9mf8fFxaFKlSoAgOnTp2Pw4MFITk7G9OnTMWbMGPb+fOvWLWRmZqJcuXJqNmVnZ7NJbBMSEjBmzBi19f7+/jh37hwAZpbk559/zq77+eef0aJFCwDA7t274ePjg7y8PMTGxmL8+PFwcnLC0qVLAQCvXr3CnDlzEBkZidevX0MulyMrK4t9w75Xr1748ccfUaNGDXTq1AmdO3dG165dYWVlhTt37kAul8PLy0vNttzcXLY+qrM///e//2HDhg1qx2jo0KHYunUrqlSpAolEgs6dO2uFPoqPj8fIkSPVlrVo0QKrV69m11euXFlvP0/p5wcPHrDhM5Xk5OToTRas2ZaUiZU1EzaePn2atR0AXFxc0KFDB2zZsgULFy5UK1u9enUQQpCVlQVfX1/s379fb6JFBwcHLXt1YeiMEkPw9vaGt7c3pFIprK2tERgYiIcPH2LlypVsOC/VttagQQM0a9YMVatWxZ49ezBs2DB2nUgkUgsr9LHc16im5Wt+TPckigXAwYwMvjK0FLtAJViIQqH+uxB0RWQoDlzrcQmXtlG/WYYe9VvJa3GNIbZZC6yxNHgpeu/tjeWXl2Nk45Fwd3Q3WY9L2z4G6ECGISgUQH5eB0exGO6urpADUI0MKRAI1B7Gly9fnv2HRXWZu7vuxqmK6oN0TTQ1dSEWi1GzZk0AwJYtW+Dr64vNmzez/wgtX74cq1evxqpVq9hQBrNnz9b6p01zyhGPxzM4u70x/wDq2o+uZaq5K1SpVasWeDwe7t69a/A+ASY8QGhoKObPn4+OHTuiTJky2LVrFyIiItgy4eHhGDBgAI4ePYrjx48jLCwMu3btQs+ePTF8+HB07NgRR48exalTp7BkyRJERERgyJAhRtmhJDMzE/Pnz0evXr201qm2La4uPoa0JapJNanmh9d89uyZQfcKysdNocfZzo7tdxhDZmamzhCHRqHxUgNgnnau756uyujRo9GnTx/2t+pDdRcXF9SsWRM1a9bE3r17Ub9+fdSpUwdNmjRBZmYmKlasqDOvRGHhJlVp0qQJYmJiIJFIIBaLUaFCBbx79w4A87KKsp/l4+ODhw8fYu7cuQgPD4etrS1CQ0Px7t07rF69GlWrVoWNjQ0CAgLYvlGFChWQkJCAM2fO4PTp0xgzZgyWL1+OCxcuIDMzEwKBANevX9fKtaY8tjEq4TeUfUZl7hGACYv5zTffIDw8HAMHDoSVlXm6+5mZmWjcuDF+//13rXXly5fXuY1mW3JxcUFWVpbW8s2bNyMlJYUNFQUw4a5u376N+fPnq/WLTp48CTc3NzbfSWH8/vvvGDVqVKFljh8/jkaNGuls825ubnj16pXaslevXsHNza1QTUC97v7+/rh06ZLesmXLloWXl5dWro+UlBQ1334s9zWqafmatO9BMQpjcmT06AFcvsx8Vw0t9fw5MHt2QTnldf38eWabH38EBg0qUl6Sn3eDq3OCaz0u4dI2TrQyM4F9+4A+fSDJzeXMNq6x5DbyqbQ3rvVKg9++9PkSgR6BuJx0GfPOz8Pm7rpDqH4qfjMGOpBhJJOXLUOvCRPwNv+fWQDw9PSEk5OTVtlMjYcQhw8fNrt9mvD5fHz77beYMmUKBgwYAJFIhKioKHTv3h3/+9//ADAzQO7du4c6deoYrOvj44OkpCQkJyejYsWKAKCVVNvHxwfbtm1jHwIAQFRUFPh8vtobl8XF2dkZHTt2xNq1azFhwgStB/3v37/X+eDi8uXLqFKlCmardKCePHmiVc7LywteXl6YPHky+vfvj61bt6Jnz54AmIcZo0ePxujRozFr1ixs3LjR5IEMPz8/JCQksA9HVNFsSxQKhUIpxfB4gCmD1oSYtp0Z8PHxwf79+0EIYd+2j4qKgoODAypXrszGaI2OjmZnWaSlpeHevXto3bo1AOb+7uzsXOS+PDw80LdvX4SFheHo0aPw8/PDy5cvYWVlhWrVquncxtvbG9HR0Rik8pAkOjqa/S4SiVCzZk21waF3Kn0/VQQCAWQyGaRSKWxtbREVFYV169axswmSkpLw9u1btW1EIhG6du2Krl27YuzYsahduzbu3LmDRo0aQS6X4/Xr12jVqpXO/enqJ6ji7OyMbt26Yc+ePdiwYYPOMj4+PoiKikJoaCi7LCoqiu0L+vj44NmzZ4X28/z8/LB79264uroW+hJOYSiTq8fFxbHf3717h0OHDmHXrl2oW7cuW1Yul6Nly5Y4deoUOnXqxC6vWrUqKleubND+unXrppbPRBfu7u56304PCAjA2bNn1RLSnz59Wmu2SlHExMSwftVFZmYmHj58iIEDB6otj42NRaNGjYzaF4VCoXCOvhkZf/4JDB0K7NwJ5N8DoZpDSDNRvcqsS3YgIzISSE8HzpwxaCDDkt8a5xqLezN77lxg1SogMRFi1UEpC0OrrlIpMGEC0KABoDE71yS9YvCptDeu9UqD33g8HiI+i0DA5gBsjdmKCc0mwNfN12Q9Lm2zdGiy76KQy4G4OAAAAfDk2TODBjEAaIVq4gJTNHv37g2BQIC1a9cCYGYwnD59GpcvX0Z8fDymTJmi9XZZUQQHB8PLywuhoaG4desWLl68qDYgYGdnh5CQEPbNxNjYWJw/fx7jx4/HwIEDtZJOGkJho4Zr166FXC6Hv78/9u/fj/v37yM+Ph5r1qzR+89lrVq1kJSUhF27duHhw4dYs2YNDhw4wK7Pzs7GuHHjEBkZiSdPniAqKgrR0dHw8fEBAEyaNAknT55EYmIibty4gfPnz8PHx8fk4z5v3jxs374d8+fPx3///Yf4+Hjs2rULc+bMsZi2RDWpJtU0vyZ9SPVpYI7jbI72WJRuWloaYmJi1D5JSUkYM2YMkpKSMH78eNy9exeHDh1CWFgYpkyZAj6fjwoVKiA0NBTTp0/H+fPn8d9//2HYsGHg8/laYYYMYeLEiTh+/DiuXbuG4OBgBAQEoEePHjh16hQeP36My5cvY/bs2bh27RoAYPz48di8eTN+/fVX3L9/H4sWLcLt27e19q2r7u/evcPLly/x7NkzHD9+HKtXr0bbtm3Zh/m1atXCjh07EB8fj6tXryIkJERtZsGePXuwefNmxMbG4tGjR/jtt98gEolQtWpVeHl5ISQkBIMGDcKff/6JxMRE/Pvvv1iyZAmOHj2qt/6afaRt27bh7du3qF27ts7y06dPx7Zt27B+/Xrcv38fK1aswJ9//olp06YBKLqfBzAzP1xcXNC9e3dcvHgRiYmJiIyMxIQJE/Ds2TOd+9X0Z/ny5eHn56c2O2HHjh0oV64c+vTpg3r16rEfX19fdO7cWSvptzHt3sHBgZ3Jo+8jEon0ak6cOBEnTpxAREQE7t69i/DwcFy7dg3jxo1jy8yaNUttgGzVqlU4dOgQXrx4gdjYWEyaNAnnzp3D2LFj2TLTpk3DhQsX2Lbas2dPCAQC9O/fX23/Fy9exGeffWZS3Q2Fan6amrTvQTEKfQMZPXsCKSmASrg8NTQHMlRRzvJQhtk28EU+iUTCvmXMBVzrcQmXtnGipXxR98IFy/WbQgESGgpBgwaA8oWVffuAn38GJk/W3c6ysoBCwslb3HEwE5Z8bpUWvzWv3Bx96/YFAcG009N0ho78VPxmDHQgQx8KBZCcDMTHA7m5zCCGlZXBgxgAE8+Ya0zRtLKywrhx47Bs2TJIJBLMmTMHfn5+6NixI9q0aQMXFxf06NHDKE0+n48DBw4gOzsb/v7+GD58uFpuB2XOjZMnTyIlJQVNmzbFV199hfbt22vFaTYU1bAJmtSoUQM3btxA27ZtMXXqVNSrVw8dOnTA2bNnsX79ep3bdOvWDePHj8e4cePQsGFDXL58GXPnzmXXCwQCvHv3DoMGDYKXlxf69OmDzz//HPPnzwfAvBk4duxY+Pj4oFOnTvDy8sK6detMPu4dO3bEX3/9hVOnTqFp06Zo3rw5Vq5ciapVq1pMW6KaVJNqml/z3r17nGtSLA9zHGdztMeidCMjI9GoUSO1z/z58+Hu7o5jx47h33//ha+vL0aPHo1hw4Zhzpw5rOaKFSsQEBCAL774AsHBwWjRogV8fHxga2trtI116tRB+/btMW/ePPB4PBw7dgytW7fGkCFD4OXlhX79+uHJkyfsixQhISGYNWsWpk2bBj8/PyQmJmLw4MFa+9ZV9+DgYFSsWBHVqlXDyJEj0blzZ+zevZtdv3nzZqSmpsLPzw8DBw7EhAkT4Orqyq4Xi8XYuHEjWrRogQYNGuDMmTM4cuQImwNj69atGDRoEKZOnQpvb2/06NFDbeaKLjT7SCKRSCtHiCo9evTA6tWr8cMPP6Bu3br4+eefsXXrVrRp0wYA08/7448/9PbzAOZh6t9//40qVaqgV69e8PHxwbBhw5CTk6N3hoYufw4fPlwtPNWWLVvQs2dPnQNaX375JQ4fPqw2w+VDXtsDAwOxc+dO/PLLL/D19cW+fftw8OBBtdxuycnJbD4UgAkDNHXqVPj6+iIoKAi3bt3CmTNn0L59e7bMs2fP0L9/f3h7e6NPnz4oV64c/vnnH7UwUleuXEFaWhq++uqrIu0sDlTz09SkfQ+KURQWWkrXywjKh3OFDWRkZzN/lQMZBj5sE4lEai8LFBeu9biES9uKrfXgAfDoEfM9OhoioVC/3s2bgJ5ZrWbn/HnY7NoFQUIC4O/PDFxs3cqsk0qBs2fVy//9N9C0KVCtGlNHHVjUcTAjlnxulSa/LWm/BNYCa5x5dAYnHpwoth6XtlksnKQX/4hQzYSemZtJEA6CcJDM3MyCQgoFye7UicQdP06yo6MJiY4mithY8vTpUxIdHU2io6MNyvSekZHBuf1Uk2pSTapJNUuXZnZ2NomLiyPZ2dmEEEL++ecfdp3qPYvy8aLrOCqPs+bxLw7maOPm0tWlmZmZScqUKUM2bdrEmaYxBAcHk//973+cauqCaqqTlZVFPDw8yOXLlznTLC6WqNmnTx/y3XffcaqpC6r5cWlydQ+hfY/SB9fH8fDhwwU/WrQghBme0L+Bcj1ASF4es+yLL9SXq34WLWLKfPUV8zsw0CC7UlNTSWpqqmmV+gB6an4rJlzaVmytn35SO37pf/9NJBERhBw5ol7u0iWmzGefGSXPmd8GDVJvZ716qf8ePpyQH38kpFkzrTqRuXN1SlrUcdABV76z5HOrtPlt2slpBOEgddbWIXnyvGLrcWlbUXDlN2PuWTRHhi6yspiZGABgbQ3UrQsen4/KYOKYicXiQmdiKNFM0sgFVJNqUk2qSTVLt2axkzVTPgrMcZzN0R7NpSsQCHDz5k3cvXsX/v7+SEtLw4IFCwAA3bt3N1nTULKysrBhwwZ07NgRAoEAf/zxB5t821RNQ6Ga6ohEImzfvl0rj0hxNIuLpWlKpVLUr18fkydP5kxTH1Tz09SkfQ+KURiT7BsAwsKA774rfEaGcp2RoaWEQqFxtnxgPS7h0rZia51Qf3PcIT+/GQAgN5d5jgYAu3Yxf8+dY46xmcKgAmDaTk4OoJwFm5kJ7N+vXubPP5m/zs5MGLS//gJ27wYyMoCrV9XLnjoF5PdNVbGo42BGLPncKm1++7bVt9gSswVxb+Kw5eYWjGw8slh6XNpmidDQUrpQjUvm6QkIBACPBx6Ph8qVKxs0iAEANjY2nJtGNakm1aSaVLN0axaVyJdSOjDHcTZHezSXrlLzhx9+gK+vL4KDgyGRSHDx4kW4uLgUS9MQVMNPNW7cGEeOHMH+/fsRHBxssqahUE1t2rRpg65du3KqWRwsTdPa2hpz5szRCgdgaXZSzY9Xk/Y9KEahL0eGPpRJvY0ZyDAwtBQhRGdceVPhWo9LuLStWFpSKXD+PPNd1707JoZpIz/+CCjDistkwL//mrY/QyAEaNMGqFWLCREPAAcOABIJFJ6eyFYJAQoAWLYMEIuBly+ZQQxdXL3KJK9/8kRjVxZyHMyMJZ9bpc1vTiInhAWFAQDmnZ+HjNyCNvmp+M0Y6ECGJoQArVpBASAFgEQZq9EEsgq7UVNNqkk1qSbVpJo6iImJ4VyTYnmY4ziboz2aSzcrKwuNGjXC9evXkZmZiZSUFJw+fRr169cvlqahiEQinDlzBu/evYNEIsGNGzfQq1evYmkaCtWkmlSTalqaJu17UIzC1AdhZpiRoVAooDB2hsgH1OMSLm0rllZUFDPQVKECMGKE9vpDh4CvvgImTFBffumSafszhMuXmVwc6enA0aPMsu3bAQDSfv2QFxTEzMIAAD4f6N8f0Hh5BQDQuDFw+zYzIAIw+TSqVQOSktgiFnMczIwln1ul0W+jm4xGTeeaeCV5heWXlxdbj0vbLA06kKEKIcCbN1DExGAOgAwAj588QaaBN1EKhUKhUCgUCoVCoVAolFKLBQ1kCIVCzkOvWGr4FS5tK5aWMqxUx45Ay5ba6xcvLgjhpMrcueYZzJg/X92OESOYpPNnzjC/Q0IgdHRkEo5fvgzExjIhrrp0Ydbz+UDt2sz32bOB+vWBbt3U9zFuHJuQvkjf/fUXcO+eQaZ/Ku2Na73S6DdrgTWWBS8DAPxw+Qc8S39WLD0ubbM06ECGEkKAli2hqFABwwH8yS4myMvLM0nSWhkXkEOoJtWkmlSTakIUSy4AAJZYSURBVJZuTQ8PD841KZaHOY6zOdqjuXSpJtWkmlSTalqOJu17UIzClDd6CTFuICMri9mPVMqE+JHJdG6Wk5ODnJwc/brJycDduwabWaReCcKlbcXSOnmS+duxI+DkBDx4AOnnnyNPNU+GKl99VfC9VSvgf/9jcmYAwMCBQNu2TF4NU3jzBggP17++dWtku7kV1DUgAPDxKbArIAD45humTkePAj17MuvCwoCgoAKdw4eZwY89ewr33fHjTLitLl2Y9rtnD/DokV7zPpX2xrVeafVbj9o90KpKK2TLsjH73Oxi63FpmyVBBzKUSCRQXL6M4QC2AmzcMA8PD4NzYmjC4/G4s49qUk2qSTWpZqnU1IxTyefTW/OngOZx5iJeqTnauLl0qSbVpJpUk2oWX5OrWNe070ExClPanVRa9EAGIQX5Cghh3oCfOBFo3px5sKwDsVgMsVisX7dSJebB9cuXBplZpF4JYrJtMpnWMTNZKzkZuHWLmfHQoQOzzNMTOHgQ5OBB7fILFwK//aa+7PffgfbtgYQEZl1kpOkzNfbtU/+t+bb5wIH66+rkxMzQWLIEqFIF6Ny5YJ2DA2PXw4fq2/TtC/uzZ+Hk7MzM3PjrL3XfrlnD/H3wgMm127cv0L27XvNLZXv7AHql1W88Hg8Rn0UAALbf2o5/n//7yfjNGCyix7J27VpUq1YNtra2aNasGf4tIgnQ3r17Ubt2bdja2qJ+/fo4duyY6TsngDgXsPFvwQ5iAEzs0XLlysHW1tZk6VxTR5WpJtWkmlSTan4ymlKpFAAgEAgAAE80EspRzEOJ9j1QcJyV03u5iHlujjZuLl2qSTWpJtWkmsXX1OxDmArte1CMwpQZGbm5hSfwzspi1qs+FJZIgA0bmO/KhOEaSCQSSPTpquY7jY01yMxC9UoYk2w7fJh5uJ+fL6JYWgBw6hTzt3FjoHx5dT3Nslu3AnPmADY2wLffamupDnBERhpvCwDs3Fnw/eefmdk3ISHM78qVgT59indMa9QAhgxRWyTs3Zv5EhvLzL7g8xn7f/21IOyWKrGxzKCNDkpde/tAeqXZb03dm2Jww8EAgAnHJyAjM+OT8JsxWJW0Abt378aUKVOwYcMGNGvWDKtWrULHjh2RkJAAV1dXrfKXL19G//79sWTJEnzxxRfYuXMnevTogRs3bqBevXrG7ZwQXNoCBCQBw/GQHcQQCATYsGEDXF1d8ebNGwiFQpPeUsnNzYWVFbcupppUk2pSTapZejQVCgXevHkDOzs7zm2j6KdE+x4aCAQClC1bFq9fvwYA2NnZmfwGrznauLl0qSbVpJpUk2oWT5P2ISglhikzMiQSoLCQ3VlZBWGllBiQJ6PQt4tVZ2HoCU1llF4JY5JtytkAgwcDoaHF01q/HhgzhvnesaNu27ZtY2Y4HDhQEMIJAL77DoiOBk6fLli2cmXB9wsXjLfn6VNmJgePx3yvXJlZ/ttvwJYtgFwOiEQQ5w/4msyWLUyd3Nz0l2nbtuC7kxOQmqq+PiwM2LwZ0PB7qWtvH0ivtPttcbvF2Be3D1efX8XhxMMIqR/CgWWW7TdjKPEez4oVKzBixAgMyR/l3LBhA44ePYotW7Zg5syZWuVXr16NTp06Yfr06QCAhQsX4vTp0/jpp5+wQTlabyhZWfmDGFAbxNi9eze+/PJLSKVSJCYmmvyGCiGE8+nEVJNqUk2qSTVLlyafz0eVKlVYnQYNGnBhGqUQSrTvkY/qcXbL/8dIOZhhKuZo4+bSpZpUk2pSTapZfE3NPoSp0L4HxShMGch4/579mnb1Kso0a6a+XtdARr9+Rcoq3y7WmTtGdSDj3TuDzCxUr4Qx2rZCjpOWVno6YGsLWFsDMTHMoMPw4cwggULBzOhQDmIAWgMZrF5oqNqAiRp9+qgPZKi+GX7xIrBxI5Oo2xBOnQI+/5z53qpVwSCGEhUfcXJMK1QAduxgcnoUxc6dwI0bQEQEM6Pj2jVg927m8+OPTOJwLm0zE1zbxqVeafdbRYeKmNNqDmaenYlvz3+L4MrB8KhQ/FxWluw3YyjRgQypVIrr169j1qxZ7DI+n4/g4GBcuXJF5zZXrlzBlClT1JZ17NgRB3XF4wPzxorq9Nt0jZvjJQDb8r+rDmIAzMGtVasWO2XXWB48eICaNWuatC3VpJpUk2pSzU9D09raWm3WX2JiIurUqVNc0yh6sIS+B6B+nHk8HipWrAhXV1fkFfa2YhGYo42bS5dqUk2qSTWpZvE1NfsQpkL7HhSjMCW0lPINdR4PNvXra6/XNZARHV3wXXOwLisL6NIF9u3aQZ7/ookWyckF39++NchMkUhkULmSwGjbEhPVf/fuzSSf5vHUtZ48AerWZQYWzpwBgoOZ5SNHMjMRBAImIbYqzZsbb9vQoUyYqYcPgfnzmWX+/syDfoWC2V+HDkC1aoXryOXqAyn9+xdanLNj+r//Aa1bI+/wYcj79oVt+fKM71Tt9fMDPvsM6NSJCaf1/j0zQ0PJ+PHA6NFA/iw6nbZlZDDhwIoR5p4LuD4XuNQrVeepHiY1n4SNNzbiYepD/HTrJ3z/2ffF1rRkvxlDiQ5kvH37FnK5HBUqVFBbXqFCBdy9e1fnNi9fvtRZ/qWe5E1LlizBfOVFUoVr167BSpGL1gA2ARhlZYXly5ejc+fOuHr1KgCgatWqUCgUSEpKAgA0bNgQDx48QGZmJsRiMby8vHDz5k0AQOXKlSEQCNjZGw0aNMDLly8hkUhga2uLunXr4vr16wCASpUqwdbWFo8ePQIA1KtXD8+ePcP79+9hbW2Nhg0bsrG63dzcYG9vjwcPHgAAZDIZkpKSkJKSAisrKzRu3Bj//vsvCCEoX748nJyccO/ePQCAt7c3UlJS8ObNG/D5fDRt2hTXrl2DXC5HuXLl4Orqivj4eKSmpqJSpUpIT0/Hq1evAADNmjXDjRs3kJeXBycnJ1SqVAn//fcfAMDT0xNZWVlIzu8YNGnSBLGxscjJyUGZMmVQpUoVPHv2DBKJBNWqVYNMJsOzZ88AAH5+frh79y6ysrJgb28PT09P3Lp1CwBQpUoVAMDTp08BAL6+vnj48CEyMzNhZ2eHzMxMtmzlypVhZWWFx48fAwDq16+Pp0+fIi0tDba2tqhXrx6uXbsGAKhYsSLs7OzwMD9RU926dfHixQukpqYiLS0N9erVY495hQoV4OjoiPv37wMAfHx88Pr1a7x79w4CgQBNmjRBdHQ0FAoFypcvD2dnZyTkxzv08vJCamoqnj17hqysLPj7++P69euQyWRwdnZGhQoVEB8fDwCoWbMmMjMz2Xbr7++PmJgYSKVSlC1bFpUrV0ZsfhzPGjVq4O3bt+zoaePGjfHff/8hJycHjo6OqFatGm7fvs22Wblczvq7UaNGuHfvHiQSCezt7VGzZk3ExMQAAHJycuDi4qLWZhMTE5GRkQGRSAQfHx/cuHEDAODu7g5ra2sk5neG6tevj6SkJLx//x42NjZo0KABoqOjkZqaCgcHB4jFYtbfderUwcuXL5GSkgKhUAg/Pz/W366urihTpgzr79q1a+Pt27d4+/Yt22afP38OiUQCFxcXuLi4sNeGWrVqIS0tjX2DWbXNOjs7w83NDXFxcWyblUgkrL8JIbh79y5yc3NRtmxZeHh44M6dOwCA6tWrQyqV4vnz52ybjY+PR3Z2NhwcHFC9enU1fyuvEampqahVq5ZR14jHjx8jPT1d7zVCeR4Zc43w8fHBq1ev9F4j3r9/z55Hhl4jlP7Wd43IzMxEtWrVjLpGKP2t7xrx/Plz8Hg8o64RtWvXZtusrmuE6jXZ0GuEZpvVvEbk5eXh2bNnRl0j3rx5Ax6Pp/cakZqaigoVKiAzM5O1icIdJd33EIvF8PPzw/Pnz5GRkVHodQUwru8hl8uRmJhY6HWF9j1o34P2PWjfg/Y9aN+D9j0oxaI4MzLs7JArlULrEa2ugQxVNAfstm8HIiMhjIxE1pAhsNV8Ix9QH8h488YgM5UvohQnV6q5MNq2qCj13/v2AY8fA9bWkObkgLi4wPbmTSAwsKCMchBDicqLPyzVq2sl1TbINj6fmdHw4EHBQEbPnsCrV8yAAACcP6+Vk0KLixfVf3/1VaHFOT2mVaogK39Whi0AVK0KLF/ODFps21aQM0NJ2bJAeDjzUXLhApPsXJdtr14BDRoAFSsyfvDyKph5Yg7OnWNCXvXrx9iuAtfnApd6peo81YONlQ0iPotAj909sPrf1RjVdBRqONWwCNtKHFKCPH/+nAAgly9fVls+ffp04u/vr3MboVBIdu7cqbZs7dq1xNXVVWf5nJwckpaWxn6SkpIIAJKWlkYUcjnJTHlFrl46Rx4nJnJSJ1Vu3bpFNakm1aSaVJNqmqyZlpbG3rMo3FDSfQ8lH0t7NJcu1aSaVJNqUk3L1KR9j9IB18fx8OHDBT/q1CGEGc7Qv4FyvfLz22/M3/LlSUZGBpFcuaK+3t6ekP37tbdTfqyt1fUXL2bXyWvU0G3DnDkF248aZVA9MzIySEZGhkFlDUHNb8XEaNtGj9b246ZNhIhEhAAkd9Ys/f7W9/HyIuTx4+LZplAQ4u3NHNN79wi5cKFAf+BAQkgRfvv6a63yhcH1MdWpJ5cXvlFmJiHduhXYfeiQbi3VNqv8pKcbZZ/BbS4tTX0/f/2ltvqD+M0CtJRwda5yaZtCoSBtt7QlCAfptbtXsfUs2W/G3LOKPw+1GLi4uEAgELBv2Sh59eoVGy9aEzc3N6PK29jYwNHRUe2jhMfnQ+zkikb+LVG1qOlrJuCjmtyIalJNqkk1qSbVLCFNSgEl3fdQ8jG1nY/FVqpJNakm1aSalqNJKcWYMiNDGVrKzg4AoKhXT319VhaQlqZ/e80ZGXJ5wapHj4D9+7W3Ue27GRhaqlTxzz/M3zZtCpYNHw5kZwMArJcsMU4vKAi4eZOZhVAceDwmhNX160CtWkDr1gW5M86fL7x9yWQFx/q334BNm4pnC1cUFeJPLAYmTy743b07sGcPxFWqwGrvXmZZVhaTUF0TZX1zcoD8mYRa/Pgj0LIlcPRo4Xb8+Sfzef+e2UaVH34ofFvKB4fH42Fp26UQ8AT4M/5PnEs8V9ImWQQlOpBhbW2Nxo0b4+zZs+wyhUKBs2fPIiAgQOc2AQEBauUB4PTp03rLG4JyOjDXmEOXalJNqkk1qSbVpJhOae570P4M1aSaVJNqUk1L0aSUYkaOZP62bq2/TJcu6r+VoaVEIsjlcsjlcnZQAwCTI6GwwQbNB8WZmeq/v/pKe5kJAxmsbRaIUbZlZgL5IQmxfTswbFjR26iG5zpxAvj994LfvXsDkZHqx8xU25T7Uh3MCgxkwlU9ewZUr46u3boBylx069YB7u7AnTvA338Dr18Dzs5M8nADkhZzfUxN1mvVCnBxKfjdty94qamwHToUuHUL2LKFSUpvb6++3fbtzN8+fZh8HMoBKoAZDOLxgAkTmFBiX3wBh/zwhlocOwZ8+SXz8fcvGLhQ5k2IjGTCfhW3nnrgUq/UnKcG4O3kjaENhgIAJp6YCJlCZrKWJfvNGEo0RwYATJkyBaGhoWjSpAn8/f2xatUqSCQSDMmPizdo0CC4u7tjSf5o8cSJExEUFISIiAh06dIFu3btwrVr1/DLL78YtD+SP7qrmnhTIpHoTMRZXMyhSzWpJtWkmlTz09FU/iWmvPlG0Utp7XvQ/gzVpJpUk2pSzeJq0r4HpUgmTGAehDZsqL/M3r3qD72Vsy1EItjY2DDfHz9mEj8rXwzRk3sMAPM2OiHMQ9tFi4DvdSS+bdWKmTGgRFXPwIEM1jYLxCjboqOZwaHKlQEPDyZR9ebN+suvWQPk5QFTpzKJqFu0YB6oDxgAXL3KJAPnyjZd2NkxCcQvXizIl9GzJ5Oz48wZ5vf06QWJtXv10srTYTbbuNITCICYGCbHSF6e+jrVc2nxYmaARi4Hxo5lZqns3w8cOcKsX7eOGfBo3Bjo21drN1VOn2aSiisUQGwsUL8+s0I1T0d+ziXUqcMMeHXrxgx0bNjADnBo1fPkSWDKFGbWSGGDmHrg8jiUmvPUQL3woHDsv7cfsa9j8cv1XzCm6RiLsK2kKPGBjL59++LNmzeYN28eXr58iYYNG+LEiRNsUs2nT5+CrzL6HhgYiJ07d2LOnDn49ttvUatWLRw8eBD1NKcm6iEjIwMA4OHhwX1lKBQKhUIxAxkZGShTpkxJm1FqoH0PCoVCoVAKh/Y9SgfZ+WGEeDweBAIBpFIpRCIRsrKyIBaLIZFIYGdnh+zsbFhbW0Mul4MQAqFQiJycHLYMIQSpqakQiUTIycmB0NcXRKGAIj1dq6xYLIYkJwdOKnbkvX0LIQCFjQ1ev34NW1tbZAuFEPv5QWhlBZ5MhrykJOh9NK1QQPr+PSQAnObO1V0mJgZSqZStkzA5mQ1Bonj9GrnZ2cjJzIR9YiIya9SA2NEREomkoE5CId6/fw9CCMqVK6ddp/yyubm5EAgEAJg3nG1sbJCdna1V1tbWFoQQZGZmgsfjIS8vj6m3nrJ5eXmFHqe8vDzk5OTAxcVF73FS/rW/eBFCALKmTZGTmQlFjRpQDXSa2acP7PfsAQBIN25Edu/eECYkQGRlBVmHDpBbWSE7NZXR8/KC2NoaktRU1k4+n69WJ/aYqtTNkDqptj1BYCBsNBN5KwcxACgSEoBr18AHkN21K/L0tT2N45Seng65XI7y5csX6nvNOukr++7dO/B4PDg5ORl/PpUvj5wjR+DYqZP+c7ZfP+RYWUEsFoO3axeEFy+CDBoEnrLAjh3Ajh2QV6sGgY7ZF5UjI5H9/j34CxbAZuVKvfsBgMxp0yCQSkEGD4bdsWMgW7YgbepUiJyd1Y6pnZUVrEaOhODpU8inTYPkzJlCfa88nwghUCgUEAqFePPmjZZfjT2flMfJ0GNq7HUvOzvbqDrpKpubm4u8vDw4OTkZVSd9bS8vLw+yHBnmtpyLyacnY865OehWoxvsBfZGX8tVj6kxdSrsOCnvDaaeT8rjlJWVVWhbVaXEBzIAYNy4cRg3bpzOdZGRkVrLevfujd69e5u0r0qVKiEpKQkODg7g8XhIT0+Hh4cHkpKSdMawLg5NmzZFdHT0J6dpLp9+DHU3hyb1J/WnJWtSf5rXn4QQZGRkoFKlSpztg8JQGvse5mjj5tKl1yLL1qT+pP60ZE3qT9r3oOhn7dq1WLt2reWFD8mfkUFsbWFraws7OzvkKd9KF4mAjAzwNPKRaZGeDhRxzvN/+AH8oCCgcWPw3rxhl/NSUgCFAqLvvoNw9WrYzpgBLFigtb2dnR0UCoVxdftA2NnZgcfjFV0QAP/ffwEA8mbNmAVlyyInKgrC4cOBli2RtWgRsGYNFLdvw7plS0AqhaJOHWTFxEBWtiyMfW9b65iagLx1a90zbfLh5z+0J87OTFkDEeWHM+MKkUhk8HHQhdzfH9KcHOT8+y8EAgHELVqw63JnzmRmwuTkAACkfftCePEiePkPeRXlyoH/7h0AsIMYec2bAytWILNWLZRt1AjWz55BERgIfny81r5zvv4aghEjYBUQANKgAfK6dYMAgCw4GIqqVcF/8gTWBw4Aw4apHVP+li0QPH3K7Dc6GoLoaPDs7WH/zTfg160LYePG4Ftbg9eiRUGoKg24aCNKuNIxB3Z2dpBKpZzqAcAw32HYeGMj4t7FYeGlhfg+SP+5og8uj0FJYhEDGR8SPp+Pyqqx//LRl4yzOAgEgk9WE+Depx9L3ak/LV8ToP7kGupPblH1J30b8uPnQ/U9zNUeP9Zzhws+lrpTf1q+JkD9yTXUn9xC+x6lg7Fjx2Ls2LFIT09HmTJlIBKJ1NqL8qGYMsSIdX6OAV0hR0T5DyStra3ZN9AB5mFYYWXZv5UqAS9eAACEEgkAQCAWQygUqr2xDLEYyMiAVRHhn6xzcmBdRKJpq9mzUQZgcnLkPwwGAJ5cDpFUCqxezdj7/ffA0qWsvco6SaVS8Pl8iEQi3XXSU3/lMs2yPB4P9ho5D/SVFak8ANZ1nFJTU2FlZcWuU6Jlp1DIhIMCYNO6NWyU+w8MBOLiAADC1FTkAXDq0IGxSblvlRBShtipJDs7W+2YGlon1d9o3x7w9ASsrHCzUyc0yj9WmvC++gr2Zcvqr7/GcUpNTYVAIIBt/iCaoXXSVzYnv13Z2dmZfD4BgHWrVkhNTYU0JQVO9vbAlSuwadkSyG9/AGA9aBDwzTdMIvDOncH382NCq6kg3LQJqFuXmQE1dCiwYIHOQQwAsJ03D3BzAx48AK9sWWa/Stu+/hqYORN2mzYBw4fDOi0NVmFhsHd2Zs8buLkBL19CHBxcIPr331C28LK1awNxcTrPkZycHJ1txJjzSekX5blg6DE15DjxeDyjz3tdZZXtzZTzXlfZ1NRUCIVCOIgd8FOXn9BueztsurUJo/xHwa+sn1FtT/Paa/C1XE9ZW1tbtXuDKeeTsqwx4SxLNNl3aWfs2LGfrKY5+FjqTv1p+Zrm4GOpO/Wn5WtSKKZirvb4KZ87H0vdqT8tX9McfCx1p/60fE0KxSzkP0wHUJAjw9YWYrEYYrG4YJ3ywbxyRkZEhG69/FCdBqHUcnBgPgAwbZp6GULYgRYlWrZZEDpte/oUOH1afdnDh0xOEGtrwM/PcC2ubTMWGxsmp0NMDF41bcokxq5fn8kVMWNGQbk+fT68bWbSY7WEQibvhGZSewcHYNw45hwJD2fyhISGMoMOAJPDRDV/SX6+P5ZDh5hcNBs2AJcuMQMRAJM7RTOp+NChjB03bwI2NnAMCYHthg1Mzg6JhMnt8eefhVfo7l0ml0ZhdeWAj+485UivbfW26FevHxREgbHHxkJBjJs9Zsl+MwYe+cSzeCnfVEhLSzPLmy2fItSn3EL9yS3Un9xC/ckt1J+fBvQ4cw/1KbdQf3IL9Se3UH9yC/Vn6YTr43rkyBF07drV+A27dWOSFNeuzTzk/N//kLpmDQAUzMioX595gK1kzx7g3Dnm4asqZ88yCb3z3+QtlL//Zh4M16wJZGcDz59rl1m0CJgzh0mk3KsXAOZNbzXbionJftOBTttat2YSZF+6xCToBpgcCoMGMcmzr1wxXItr24rBkSNH0LVlSybxuIMDEBkJtG0LVKgAPHvGLC8h27jUM1hLodAe5Hj8mJn1pHE+XJsxA01++YUZ5PjpJ8CYMFidOwPHj+tet2MHkzTe2xu4d49ZVqUKM5imSocOwKlTWpuXiN+MgKtz1dzt7Xn6c9ReWxuZ0kxs7rYZQxsNLTHbAO78Zsw965OfkWFjY4OwsLBSk73dEqA+5RbqT26h/uQW6k9uof78NKDHmXuoT7mF+pNbqD+5hfqTW6g/KWZF2a5UZmSohoMBUDAjQ4mjI6ArSXF6OpCSorYo5/p13ft9+ZL56+bGvNGvC+VDfpWcM1q2WRBatuXkFNRBdcDin3+YvwEBhmtxbRsXODkVzKYJCgK2bAEOHzZqEMMctnGpZ7CW5iAGAFSrpnNQL7llSyA1FVi71rhBDABYsULtJxEIAFdXZgZI//7Mwn37gGHDmAGMJ0+AqChmFlBiImPn6dPAnTtM2YwMZuAJ+XUVCpmBEiMSO+viozpPOdZzd3RHeFA4AGDGmRlIyU7Rs6X5bSsp6ECGjQ3Cw8Npx41DqE+5hfqTW6g/uYX6k1uoPz8N6HHmHupTbqH+5BbqT26h/uQW6k+KWdEcyBCJkJeXp55sVtdAhq0tsHGj+nIdAxnS6tWRtW+f9n4TE5m/FSoA+hLvKmdpKAc9AG3bLAgt22JiAJmM+a58cAwUDGoUMpDBdT3N7jcejwmb5O9v9KaWXFeLa2+1azPni6cniI0NJJcvM2Ha1q0DBAKmTP36wKZNgIcH8zswEKhRgxlY+fJLZlmDBkxYq6AgZlbU7dtM0vCwMGbWx5gxTLnERGDyZN0zpgrB4vymwodobxOaTUCd8nXwNust5pybU2K2lRSf/EAGhUKhUCgUCoVCoVAoFAqFY5RvjCvfwLa1BZ/PB1/1DXPNN+yVb+EPH84k7e7dm/mtYyCDLxRC0bFjQVglJflJrVGhQsHDfk0ePGD+qgxkaNlmQWjZdu1awXdlaK6nT5kcBwATWspQLa5tsyAsua4W6TehELhyBVnR0UCdOsZtO3VqwfcePZi2mJsLfP01xIGBsFHO+PjtNyY0VkgIsGoVMGGCUbuxSL/l8yHam1AgxNrOawEAG65twPUXemammdm2kuLjrwGFQqFQKBQKhUKhUCgUCsWy0JzpIxKBx+OBpxryRjP0k2p89DJlCn5rDmQMH16g5eysrqEcyHBzA/S9gZyZyfxVGcjQss2C0LJNJSQW4uKACxeAqlWZ3+7uBW/MG6LFtW0WhCXX1WL9Vr48UKOG8bY1awa0aaO9/PJlCP77r+C3XM7kz1HOHjpwgGnDDx8atBuL9Rs+XHtrU60NQuqHgIAYnPjbkv1mDHQgg0KhUCgUCoVCoVAoFAqFwi2aAxm2ttrhTRQaD+A0E72qDmS8e8d879gR2LixQEszeW18PPO3QgVgxozCbUxOZr9acugVLdtUBzJycoDPPiv4XUhYKZ1aXNtmQVhyXUul344cASZOZL5Xrw7Uq6e+/vvvmb/KcGgODgAhQN26TBiqX381yDZ5bKz+sHElyIdsb8s7LIeDtQOuPr+KrTe3fnDbSopPYiBj7dq1qFatGmxtbdGsWTP8+++/hZbfu3cvateuDVtbW9SvXx/Hjh37QJZ+PBjj040bN6JVq1ZwcnKCk5MTgoODizwGnxrGtlElu3btAo/HQ48ePcxr4EeGsf58//49xo4di4oVK8LGxgZeXl70vFfBWH+uWrUK3t7eEIlE8PDwwOTJk5GTk/OBrLVs/v77b3Tt2hWVKlUCj8fDwYMHi9wmMjISfn5+sLGxQc2aNbFt2zaz20kpPrTvwT2078EttO/BLbTvwS2078EdtO9BKVE0kxGLRNoJZzVnZChDSynRNSOjXDkAKslrNfNsKGdbVKgAfPstE6tfH2/esDZYcjJc1racHKBnz4LBGuUsDNWHun5+hmlxbZsFYsl1LZV+s7cHIiKA9euBY8eADRsAOzvIhgxBbnQ0MH16Qft0d2dyaagyeDAzUDl1KvDHHzp3Id61C47NmwMjRhhvn5n5kO2tokNFLGi7AIBhib8tub0ZQ6kfyNi9ezemTJmCsLAw3LhxA76+vujYsSNev36ts/zly5fRv39/DBs2DDdv3kSPHj3Qo0cPxCpjDlKM9mlkZCT69++P8+fP48qVK/Dw8MBnn32G50Ym9CmtGOtPJY8fP8a0adPQqlWrD2Tpx4Gx/pRKpejQoQMeP36Mffv2ISEhARs3boS7u/sHttwyMdafO3fuxMyZMxEWFob4+Hhs3rwZu3fvxrfffvuBLbdMJBIJfH19sXbtWoPKJyYmokuXLmjbti1iYmIwadIkDB8+HCdPnjSzpZTiQPse3EP7HtxC+x7cQvse3EL7HtxC+x6UEkXHjIzs7GxkZ2cXLNMcyFAmFVaiHMj47beCGPz5oaRYLU0NJW5uTMz/M2eAzz/XXUahYAYzVPW4RqFg8n0UA9a2X34BlAOSHh5Au3bahZs2NUyLI8zmNw6w5LqWWr8JBMDo0Uzy8BYtAIkEGRERyPL0ZBK3r1zJ5N/YuBFo2xbQ7FeeOgWsWAEMGKAW+g0AkJICgfL+vmMHoBqyygL40O1tnP841Hetj3fZ7zD77OwPaluJQUo5/v7+ZOzYsexvuVxOKlWqRJYsWaKzfJ8+fUiXLl3UljVr1oyMGjXKrHZ+TBjrU01kMhlxcHAgv/76q7lM/KgwxZ8ymYwEBgaSTZs2kdDQUNK9e/cPYOnHgbH+XL9+PalRowaRSqUfysSPCmP9OXbsWNKuXTu1ZVOmTCEtWrQwq50fIwDIgQMHCi3zzTffkLp166ot69u3L+nYsaMZLaMUF9r34B7a9+AW2vfgFtr34Bba9zAftO/x6ZCWlkYAkLS0NE70Dh8+bNqGCxcSwgSOYT7btpHc3FySm5tbUMbfX72MJhs3qq8HCJk3jxBCCrSGDNEuAxCSmFigI5cTcucOIYMGaZe7eVNdjyNYvw0dSoiVFSGxsSZrsbaNG1dgd5s2hKxYoV6X9esN1+IIs/mNAyy5rlzbRgh3vvugfnv8mJDwcEJ++kn73Jw6lSnz5Akhkydrr+/blxP7Pkq/5fP3478JwkF44Tzy77N/P5hthHDnN2PuWaV6RoZUKsX169cRHBzMLuPz+QgODsYVZVIZDa5cuaJWHgA6duyot/ynhik+1SQrKwt5eXlw1kzI9Qliqj8XLFgAV1dXDBs27EOY+dFgij8PHz6MgIAAjB07FhUqVEC9evWwePFiyPW91fMJYYo/AwMDcf36dTYExKNHj3Ds2DF07tz5g9hc2qD3pI8P2vfgHtr34Bba9+AW2vfgFtr3KHnoPYnCKZqhpWxtIZFIIJFICpZp5sjQRDPUFMCGlmK1NPejpEKFgu98PhOvv2JF7XL5b31r2cYVW7YAMhnzlrmJsLbdv1+wsGxZoH79gt/t2zNvwhuqxRFm8xsHWHJdqd/yqVoVCAsDxo4Fnj4FXF0L1kVEMDM2qlZlZnLkk7VkCfNlzx5uZ2UQUqzNS6K9taraCgMbDAQBweijoyFTyD6IbSVFqR7IePv2LeRyOSqo3rwAVKhQAS81pyfl8/LlS6PKf2qY4lNNZsyYgUqVKml1kD9FTPHnpUuXsHnzZmzcuPFDmPhRYYo/Hz16hH379kEul+PYsWOYO3cuIiIisGjRog9hskVjij8HDBiABQsWoGXLlhAKhfD09ESbNm1oeAcT0XdPSk9PLx3TQkshtO/BPbTvwS2078EttO/BLbTvUfLQvgeFUzRDS4lEEIvFEIvFBcuKGsTVTP4NsKGlWK1vv2Xi7dvbq28nEmlvq/qQVEn+9UXLNi5ITy/4zjf9EZxYLIbYzg64fr1g4eLF6gMZ/v6Ga3FYT7P4jSMsua7Ubzrw8ACSk5nrQoMGzLJLl9SKyAcOhNWUKcCXXzIDDwsXApGRTPnTp4vex61bBfl2VPnrL+Yc5fGA3bsLlr9/D/j6Am3aMAOShVBSfvvhsx/gZOuEG8k38NO/P30Q20qKUj2QQbE8li5dil27duHAgQOlIsnMhyYjIwMDBw7Exo0b4eLiUtLmlAoUCgVcXV3xyy+/oHHjxujbty9mz56NDRs2lLRpHyWRkZFYvHgx1q1bhxs3buDPP//E0aNHsXDhwpI2jUKhfKLQvkfxoH0P7qF9D26hfQ8KxYLRkSND663giRML1yhkIIPVqlIFSEpSn/GgMSCnc3mZMszf5GR1PS65e7fg+9u3hm1z4gRTp4sX2UUSiQRZ9+4xGgIBM0Di48PUp3x5ppCBAxmWPEuBayy5rtRveuDzmc+CBerLW7YE7t1D+ooVjNa8eczyPXuA/v2BO3eAMWO0BxtycoD9+5lBTEdHoGFDoEMHIC+PWQfASiIBunUr2KZfP+Czz4C1a5nz6/Zt4MIFYNMm7uppAIbquYpdsazDMgDAnHNzkJSWZHbbSgqrkjbAnLi4uEAgEODVq1dqy1+9egU3Nzed27i5uRlV/lPDFJ8q+eGHH7B06VKcOXMGDZQjq584xvrz4cOHePz4Mbp27couU+RPxbWyskJCQgI8PT3Na7QFY0r7rFixIoRCIQQqSeV8fHzw8uVLSKVSWOubpvwJYIo/586di4EDB2L48OEAgPr160MikWDkyJGYPXs2+MV4C+lTRN89ydHRESJdb5hRShza9+Ae2vfgFtr34Bba9+AW2vcoeWjfg8IpmtczkUj7pYJBg4Dhw/W/6axrICM/tJSaFo/HLgfAJPrWheqMjMaNgXPn2BkZZnnhIT6+4HtsLDB7NvPAtFkz9XJbtwKJicCkSQWJybt1A1JTWdv4yhA69eqph9xavhz4+2/AwJB6XNfTkl8UseS6Ur8VQffuwMmTzDnaty/QqBGjpZwd2KABMytj//6CpOAPHgDbtwNDhzK/Hz0CdPVTb9xQuz59rmv/p09rz/AICwNCQnSHvEPJ+m1oo6H49davuPT0EsYfH4+D/Q6a1baSolT36qytrdG4cWOcPXuWXaZQKHD27FkEBATo3CYgIECtPACcPn1ab/lPDVN8CgDLli3DwoULceLECTRp0uRDmPpRYKw/a9eujTt37iAmJob9dOvWDW3btkVMTAw8PDw+pPkWhynts0WLFnjw4AH7UAYA7t27h4oVK37SDxIA0/yZlZWl9cBA+aCGFDPe5KcIvSd9fNC+B/fQvge30L4Ht9C+B7fQvkfJQ+9JFE7RMSMjLy8PeXl5Bct4PCZcUo0awG+/aWsUMiNDS0t1IEPfjAzNgQyAfQiqpccFCQkF3x88YMJBNW+uXiYri3nwunCheh3ev2e/ksOHYdO/P/PDz099+9BQYPNm/blCNOC6nmbxG0dYcl2p3wzgs8+ApUvZQQwtLeWsDABQhpBdsADIzQVWrdI9iFEYZ88yH02GDgVq1gRev2YGMq5cAd680QqNV5J+4/P4+PmLnyHkC3Eo4RAO3j1oVttKDE7Si1swu3btIjY2NmTbtm0kLi6OjBw5kpQtW5a8fPmSEELIwIEDycyZM9nyUVFRxMrKivzwww8kPj6ehIWFEaFQSO7cuVNSVbA4jPXp0qVLibW1Ndm3bx9JTk5mPxkZGSVVBYvCWH9qEhoaSrp37/6BrLV8jPXn06dPiYODAxk3bhxJSEggf/31F3F1dSWLFi0qqSpYFMb6MywsjDg4OJA//viDPHr0iJw6dYp4enqSPn36lFQVLIqMjAxy8+ZNcvPmTQKArFixgty8eZM8efKEEELIzJkzycCBA9nyjx49InZ2dmT69OkkPj6erF27lggEAnLixImSqgLFAGjfg3to34NbaN+DW2jfg1to34NbaN/j0yQtLY0AIGlpaZzoHT582LQN9+4lhIliz3zu3CHp6ekkPT3dcI2UFHUNgJC3bwkhRFvrzp2CMmPH6tZ7+5YQgYAQsZiQ335jyrZurVuvmBw+fJiQnj217Vd9FCeTERIRobsMQIhCwZRTXfbTT8Wyi+t6msVvHGHJdeXaNkK4891H5bfNm5lzSCIhxM2NOUc6dlQ/Z0QiQo4fJ+TkSULu3SOkQgXtc2306AJNqZSQtm0JadKEkAMHCMnLI2TfPu1tgoIKzlGO62mq3uyzswnCQdwj3El6TsG2ltzejLlnlfqBDEII+fHHH0mVKlWItbU18ff3J//88w+7LigoiISGhqqV37NnD/Hy8iLW1takbt265OjRox/YYsvHGJ9WrVqVAND6hIWFfXjDLRRj26gq9GGCNsb68/Lly6RZs2bExsaG1KhRg3z33XdEJpN9YKstF2P8mZeXR8LDw4mnpyextbUlHh4eZMyYMSQ1NfXDG26BnD9/Xuf1UOnD0NBQEhQUpLVNw4YNibW1NalRowbZunXrB7ebYjy078E9tO/BLbTvwS2078EttO/BHbTv8WliMQMZhw6pP/R78IBIJBIikUgM18jL0354mH+91NJ6/rygzMKF+jUPHCDkzBlCIiOZsl5euvWKyeHDhwmpU0f3AEVKClNo1Sr9gxgAIS9fMvVVXXblSrHs4rqeZvEbR1hyXbm2jRDufPfR+m3NGu1zaNYs7XLR0cyAYF4eIYSQYzt3qg1I6EShICQgQFv/jz8Ms80ETNHLkmYRz9WeBOEgE49PNJtthJTMQAaPEDrflkKhUCgUCoVCoVAoFAqlNJCeno4yZcogLS0NjrpCMxnJkSNH1HIlGczJk0CnTgW/nz3De7EYAFC2bFnDdXg89d/5j7He54deYrVycwFlHPhffgFGjChcNyEBqF2bCV+VlqatV0z+OngQX/TpwyQV9vZWDzN19SqTnNvREcjI0C9y/jxQsSJjp5KsLKAYOWu4rifXeia3Nx1Ycl25tg3gzncfrd9ycoBatYBnz5g8OWvWAL16ASp5yXRhsN+Sk5nwcBcvArduMcuqVAHu3gVEInXbcnOBHTuALl2Yc9gETPXb6Yen8dlvn4HP4+Pq8KtoUqmJRbc3Y+5ZpTpHBoVCoVAoFAqFQqFQKBQKpQTQzJEhEkGU/zGZy5dV5DS0bGyA/IESvTkyVFE+XExPB7Kyim+bBqJXr5hBDFtbQDPPzP37wMSJhQ9iAEyy8Js3C3736lWsQQxAh9+KCdd6XGLJdaV+M4OWrS2wbh1Qrx6wbx/Qu3eRgxhGUbEi8OOPQEwMIJEAlSsDT58CdeoAixZBfPo0RFIpM6AyaRIzmNqzJ6CSF80YTPVbB88OCKkfAgVRYNRfoyBTyCy6vRkDHcigUCgUCoVCoVAoFAqFQqFwi45k31lZWcjKyjJNj89XGxDQqeXuzvytWrVoPQeHgkGBly8L9C5dYpL6FhP758+ZL15e2ivj4pi3xVU5fx7IzAQOHADGjCkolz+QkTt4MPNwtpgU6xh8AD0useS6Ur+ZSatrV+DOHaBFC072pxc7O2DJEub748fA3LkQ9ukDmwoVmOvKhg3MuqtXgd9+M2kXxfHbio4r4GTrhBvJN/DTvz9ZdHszBjqQQaFQKBQKhUKhUCgUCoVC4RZra/XftrYQi8UQK2dNGIvGm9U6tbZsYR4gNmhQtB6Px4SfAYCXLyEWi2EfHQ20asXM6Ni92zQ787F/9oz5Urs20L27+srFi9V/N28OBAYyM0p69ACaNGGWx8czb38DEDRtqh1mywSKdQw+gB6XWHJdqd9KXqvYDBgANG6sf71yQHXGjKJnX+mgOHV1Fbvi++DvAQBzzs3BO9k7y/FbMaADGRQKhUKhUCgUCoVCoVAoFG5RnZFhbQ3w+ZBIJJBIJKbpaQxk6NRq0QIYNcrwB/4qAxkSiQTyvXsL1vXrZ5qd+bAzMpQDGYcOac/CUHLlivrAT506zN+zZ4FTpwAAWbpmdphAsY7BB9DjEkuuK/VbyWsVGz6fOUcPHgQWLYK8WrWCdZ9/Dly7BtSsCbx8CcyaxYSxM4Li1nWY3zC0rNISkjwJvj76NTIzM03WshToQAaFQqFQKBQKhUKhUCgUCoVbVAcy8kM42dnZwc7OzjQ9Kyu1n8XSUqIcyPjyS9ilpUHIL8ZjsufPgZQU9ic7I8PbmxlY6dYNaNNGe7vgYO1lqsm987FRztIoJpz4zYx6XGLJdaV+K3ktTihThhmonD0bsv/+Q97GjUBiInDsGODiAqxYwZRbu5Ype+YMQIhB0sWtK5/Hx8auG2EtsMaZJ2dwKPGQyVqWAh3IoFAoFAqFQqFQKBQKhUKhcIvqDANbWwBAdnY2srOzTdOrWVPtZ7G0lCgHMgDwvvkGMs23nw3VT0lhEv+qDECozchQ4umpvl2rVsCePdp6Zcqo/SS2tihmTVk48ZsZ9bjEkutK/VbyWlyTLZVC8tVXgOrMjC++UB+s7NABmD2b+b57N9CoEbByJRMOb+hQtVkbXNS1tktthAWFAQCmnpmK15Li5/8pSehABoVCoVAoFAqFQqFQKBQKhVt0zMiwtraGtWbujKKIjGQeBO7apbbYJC1NKlZkvwqePoVVcrL6euVgRFFERzN/37wBUlOBd+9gk5bGLFMNCaX5dvWIEYCTU9H6NjbFr2s+nPjNjHpcYsl1pX4reS2u0Wkbjwds2wb4+xcsW7IE6NiRCV8XEwNMmcIkKN+6FZg6tXA9E5geOB31y9dHak4qJhyfUGy9ksSq6CIUCoVCoVAoFAqFQqFQKJSPCeWbvDweDwKBAFKpFCKRCFlZWRCLxZBIJLCzs0N2djasra0hl8tBCIFQKEROTg5bhhCC1NRUiEQi5OTkQCgUghAChUKhVVb5VyQSITc3F8p5BXJra+Tl5LA6ubm5bFlbW1vk5eWBz+eDx+MhLy8Ptra2yM7OZso0aADx0aNM2exs5OXlgcfjITv/u0AgMLpOyr/2zs4QKm0kBPynT9V8KG/bFvK4OEhkMtZuQX6uDrlcDhsbG2RnZsLx+HEoM3ikx8TABoANAIW7O7J5POS9f8/Wyf7cOVh17Qri64u0du3U6qR6nOTLlsHum2+YYzliBFJTU9n9Flanoo6T6jHQWyel71V09R2nwo6pKW2PEAKpVGpUnXS1PYFAwOQ9kcvB5/ONqpO+smlpaeDl518x9XxS/lUoFMjNzQUhxKg6FXacCCHseWFonXQdJ9Vjakyd9B0nXW3E1LaXlZUFmUxW5DE1tu1lZ2ebdD6plpXL5ZBKpVAoFOp1srOD+OJFSHfuhP2QIcyFIj/3jRabNiFv0CBk1qvH2qU8jsW5li9rsQxfHPoCu//bjS+9v0QHjw5Gn0+ax0l5bzD1fFLWKSsry+D7Gp2RQbE4tm3bhrJly5a0GSbD4/Fw8ODBQssMHjwYPXr0+CD2WBpz587FyJEjP8i+IiMjwePx8P79+0LLVatWDatWrTKrLcbug6vzwJD2aCxxcXGoXLmy5STYolAoFIrJqN4nHj9+DB6Ph5iYmEK3SUhIgJubGzIyMsxvIAy7h4aHh6Nhw4ZmtcOUfXBxHzZXv7F58+bYv38/57oUCqXkWLt2LerUqYOmTZuWtCkMQmHB9/zQUsqHtpYCyZ8pooSvMQND8OwZ+Dt2FKph+913EKxeXbBNbCx49+4BABS1amnvs0ULvE9Kguz8ee0ZGirkDhsG6ePHyNy8GVnTphVZF0Ph+hhY2jFVxRx2caVp6X6z1DZi6X4rjLzu3SGNi1NblrtkCeRBQcg4fhzyr74CAAgmTABkMk7rWq9cPYxtNBYAMPHURKTlpnGi+8EhFIoZCA0NJQC0Pvfv3y9y261bt5IyZcqYzbatW7ey9vB4POLu7k4GDx5MXr16xYl+cnIyycnJIYQQkpiYSACQmzdvqpV5//49SU1N5WR/+ggLC2PryefzSeXKlcmIESPIu3fvjNIJDQ0l3bt358Sm5ORk4uDgQB4/fqymr7RTKBQST09PMn/+fJKXl1fs/eXm5pLk5GSiUCgIIfrb1uvXr4lEIin2/gqjatWqZOXKlQaX5+o8AEAOHDhg1DaLFi0iAQEBRCQS6bXhyy+/JAsWLCi2fRQKhfKponr/s7KyItWqVSPTp08n2dnZH9QO1fuEvn6LJj179iSLFi1if58/f16tv+fq6kp69epFHj58yImNmvdpXfe2jIwM8vbtW072p4+wsDDi6+tr1Dam3Ic1MaUvduHCBfLFF1+QihUr6rXhyJEjpGbNmkQulxfLPgqFYnmkpaURACQtLY0TvcOHD5u2YV4eIUxaW0ICAgghhGRlZZGsrCxO7OJE6+RJ1kZFxYoF9vbsWfA9PLxwDWU5XZ+xY4tnXz4W5zcz6pnc3nRgyXXl2jZCuPMd9ZtpGGzbo0eEHDhAyH//qS9/9YqQsmWZa0edOkQ6YwbJjo/nzLZ3ae9IrTW1CMJBRhweUWxNrvxmzD2LhpaimI1OnTph69atasvKly9fQtao4+joiISEBCgUCty6dQtDhgzBixcvcPLkyWJru6kkC9NHGY3EXeaibt26OHPmDORyOeLj4zF06FCkpaVh9+7dH2T/mmzatAmBgYGoWrWq2nJlW8nNzcWxY8cwduxYCIVCzJo1q1j7s7a2Nuh4WEq7tBSkUil69+6NgIAAbN68WWeZIUOGYMSIEZg1axasrOithEKhUExBef/Ly8vD9evXERoaCh6Ph++//76kTdPL06dP8ddff+HHH3/UWpeQkAAHBwfcv38fI0eORNeuXXH79m12KrqpGHKftre3h729fbH2U5qQSCTw9fXF0KFD0atXL51lPv/8cwwfPhzHjx9Hly5dPrCFFArFEpDL5cjLyyuynJWVFXJyckzbSfXqgEIBVKkC5OQgPT+RrTI8T3HgRKtVKyA0lMnDAQBVqwLOzoC7O/MdYHJ9FFZ/jf9v1WjYsPBtDcTi/GZGvWK1Nw0sua5c2wZw57vS4jehUFjsfqgxKH0v0pjppUX16sxHE1dXYPFiYMwYIC4Owrg4CL//nlk2fTpQjGcvOTk54IGHTd02IWhbEDbe2Ih+9fqhXfV2JmuWBPTpE8Vs2NjY6HyIvGLFCmzduhWPHj2Cs7MzunbtimXLlun95/PWrVuYNGkSrl27Bh6Ph1q1auHnn39GkyZNAACXLl3CrFmzcO3aNbi4uKBnz55YsmQJxGKxXtt4PB5rW6VKlTBhwgTMnTsX2dnZsLGxwaJFi/DLL7/gzZs38PHxwdKlS9GpUycAzEPeKVOmYP/+/UhNTUWFChUwevRo9qE7j8fDgQMH0KNHD1TPvzA1atQIABAUFITIyEgMHjwY79+/x8GDB/HLL78gPDwcz549A59fEO2te/fuKFeuHLZs2QIAOHToEObPn4+4uDhUqlQJoaGhmD17dqEPka2srNh6uru7o3fv3mqDS3K5HCNHjsS5c+fw8uVLVKlSBWPGjMHEiRMBMCEUfv31V7ZeAHD+/Hm0adMGSUlJmDp1Kk6dOgU+n49WrVph9erVqFatml57du3aha+//lpruWpb+frrr3HgwAEcPnwYs2bNQmpqKiZOnIgjR44gNzcXQUFBWLNmDWrlT9F98uQJxo0bh0uXLkEqlaJatWpYvnw5OnfujMjISLRt2xapqamIiYnBkPxYhMq6hIWFITw8HNWqVcOkSZMwadIkDBgwAHK5XG2wJy8vDxUrVsSKFSswaNAgKBQKfP/99/jll1/w8uVLeHl5Ye7cufgqfxqgIRh6Hhw8eBDTp09HUlISgoKCsGnTJnh4eLDrTWkXRTF//nwATHgrfXTo0AEpKSm4cOEC2rdvb/K+KBQK5VNG9f7n4eGB4OBgnD59mh3IMOR+899//2HGjBn4+++/QQhBw4YNsW3bNnh6eiI6Ohrffvstbt68iby8PDRs2BArV66En5+fyTbv2bMHvr6+cHd311rn6uqKsmXLomLFipg3bx5CQkLw4MEDeHt7Y/369fjhhx+QlJSE6tWrY86cORg4cCAAZhr+/PnzsWXLFrx69QrlypXDV199hTVr1gCA2n1a2c/o2bMnAKBq1ap4/PgxwsPDcfDgQcTExODUqVPo1q0bXr58qRamceLEibhz5w7OnTsHwLQ+pCqG+jc5ORmff/45IiMjUbFiRSxbtkztGJrSpyqKzz//HJ9//nmhZQQCATp37oxdu3bRgQwK5RODEIKXL18WGYJXiaurKxITE03b2fr1zNwEkQhITGTDpKSkpJimpwJnWtOnM0l3lVhbMw8MlddGsRjQV39CgA0b9Gu7uurf1ggs0m9m0itWe9PAkuvKtW0Ad74rTX4rW7Ys3NzcOB0w0oehfchCGTkS2LIFuHatYNm33zKfBg2AzZuB/OehptjW2qk1vm7yNdZfW48RR0bgztd3YCfUH+LO0qADGZQPDp/Px5o1a1C9enU8evQIY8aMwTfffIN169bpLB8SEoJGjRph/fr1EAgEiImJgTA/1ubDhw/RqVMnLFq0CFu2bMGbN28wbtw4jBs3Tms2SGGIRCIoFArIZDJs2LABERER+Pnnn9GoUSNs2bIF3bp1w3///YdatWphzZo1OHz4MPbs2YMqVaogKSkJSUlJOnX//fdf+Pv748yZM6hbty6sra21yvTu3Rvjx4/H+fPn2QfCKSkpOHHiBI4dOwYAuHjxIgYNGoQ1a9agVatWePjwIZtnIiwszKA6Pn78GCdPnlSzQaFQoHLlyti7dy/KlSuHy5cvY+TIkahYsSL69OmDadOmIT4+Hunp6aw/nZ2dkZeXh44dOyIgIAAXL16ElZUVFi1ahE6dOuH27ds665mSkoK4uDh2AKowRCIR3r17B4CJC33//n0cPnwYjo6OmDFjBjp37oy4uDgIhUKMHTsWUqkUf//9N8RiMeLi4nQOigUGBmLVqlWYN28eEhISAEBnuZCQEPTu3RuZmZns+pMnTyIrK4t9aLJkyRL89ttv2LBhA2rVqoW///4b//vf/1C+fHkEBQUVWT/AsPMgKysL3333HbZv3w5ra2uMGTMG/fr1Q1RUFADT2kWbNm1QrVq1QgcpDMHa2hoNGzbExYsX6UAGhUKhcEBsbCwuX76sNmuxqPvN8+fP0bp1a7Rp0wbnzp2Do6MjoqKiIJPJAAAZGRkIDQ3Fjz/+CEIIIiIi0LlzZ9y/fx8ODg4m2Xnx4kWD7+UA8wLIgQMHMHHiRKxatQrBwcH466+/MGTIEFSuXBlt27bF/v37sXLlSuzatQt169bFy5cvcevWLZ260dHRcHV1xdatW9GpUyedb9m1b98eZcuWxf79+zFs2DAAYF9S+O677wBw04c01L9z587F0qVLsXr1auzYsQP9+vXDnTt34OPjY1Kfatu2bRgyZAgnMZP9/f2xdOnSYutQKJSPC+UghqurK+zs7Ip8wJeeng5HR0fTdpadzczIcHQEqlRh71FczOrmTIsQZtaE8rrq4AA4OQHKxN9ise63pwFAKgUKS1RbsyYzMFJMLNJvZtIrVnvTwJLryrVtAHe+Kw1+I4QgKysLr1+/BgBUrFix2PsuCmUeUV39N4MRCICzZ4Fr15Bz8CBsVWdB374NdOsGJCQw1ykTbVsavBRH7h3Bo9RHmHd+Hn747AfT7f3QcBLMikLRIDQ0lAgEAiIWi9nPV199pbPs3r17Sbly5djfmrkBHBwcyLZt23RuO2zYMDJy5Ei1ZRcvXiR8Pl9vjGlN/Xv37hEvLy/SpEkTQgghlSpVIt99953aNk2bNiVjxowhhBAyfvx40q5dOzbvgiYwINa0Zqzj7t27k6FDh7K/f/75Z1KpUiU2ZnH79u3J4sWL1TR27NhBKlasqNMGQpg4znw+n4jFYmJra8vGrV6xYoXebQghZOzYseTLL7/Ua6ty397e3mo+yM3NJSKRiJw8eVKn7s2bNwkA8vTpU7XlqvoKhYKcPn2a2NjYkGnTppF79+4RACQqKoot//btWyISiciePXsIIYTUr1+fhOuJWaqM2a3MR6Iv74Rq/oq8vDzi4uJCtm/fzq7v378/6du3LyGEkJycHGJnZ0cuX76spjFs2DDSv39/nXZo7kMXus4DAOSff/5hl8XHxxMA5OrVq4QQw9qFanskhJCBAweSmTNn6rVDlaLydPTs2ZMMHjzYIC0KhUKhqKPaV7KxsWFzWu3bt48QYtj9ZtasWaR69epEKpUatE+5XE4cHBzIkSNH2GWG9FtU8fX11cqRpHm/ffHiBQkMDCTu7u4kNzeXBAYGkhEj1OPw9u7dm3Tu3JkQQkhERATx8vLSWw/Ne6jmvY0Q7fwVEydOJO3atWN/nzx5ktjY2LA2mtKHLCpHhj7/jh49Wq1cs2bNyNdff00IMaxPpdkX+/PPP4m3t7deOzTR5S8lhw4dInw+n+bJoFBKGYXFG5fJZCQuLs6ovELFyu948yYh0dGE5OdNksvlnF1zuNQit28zdkZHE/LkCSEKBSEvXjC/79xhymRlMeXi4wnJz4tJ0tMLtnv5suC78qPnuYGxWKzfzKDHZT5RS64r17YRwp3vSpPf3r59S+Li4ohMJtNbhqtcD7m5uSQ3N5cTLVYvPp6QVq3Uc+8MHEjI8+fFsu2vhL8IwkH48/nkStIVk+yjOTIopYq2bdti/fr17G/lNKYzZ85gyZIluHv3LtLT0yGTyZCTk4OsrCzY2WlPZ5oyZQqGDx+OHTt2IDg4GL1794anpycAJuzU7du38fvvv7PlCSFQKBRITEyEj4+PTtvS0tJgb28PhUKBnJwctGzZEps2bUJ6ejpevHiBFi1aqJVv0aIF+2bg4MGD0aFDB3h7e6NTp0744osv8NlnnxXLVyEhIRgxYgTWrVsHGxsb/P777+jXrx8baurWrVuIiopi3yIEmDcLC/MbAHh7e+Pw4cPIycnBb7/9hpiYGIwfP16tzNq1a7FlyxY8ffoU2dnZkEqlaNiwYaH23rp1Cw8ePNB6mzMnJwcPHz7UuU12djYAwNbWVmvdX3/9BXt7e+Tl5UGhUGDAgAEIDw/H2bNnYWVlhWbNmrFly5UrB29vb8THxwMAJkyYgK+//hqnTp1CcHAwvvzySzRo0KBQ+wvDysoKffr0we+//46BAwdCIpHg0KFD2LVrFwDgwYMHyMrKQocOHdS2k0qlbAgxQzDkPLCyskLTpk3ZbWrXro2yZcsiPj4e/v7+JrWL7du3G+WPwhCJRMgq7O0jCoVCoRSKsq8kkUiwcuVKWFlZ4csvvwRg2P0mJiYGrVq1YmeqavLq1SvMmTMHkZGReP36NeRyObKysvBU+YapCWRnZ+u8lwNA5cqV2bfffH19sX//flhbWyM+Pp6dMaikRYsWWL16NQBmduqqVatQo0YNdOrUCZ07d0bXrl2L9dZeSEgImjdvjhcvXqBSpUr4/fff0aVLFzbUlKl9SFUM9W9AQIDW75iYGNYOY/tUPXv2ZGeJFhflrOTc3Nyi4zlTKJRSgTInhr7/ITlHGT45/69Cocj/yde3hcFwqQWhEMjNZb5bWwM8HjMr4/lzZtYFIcDjx0yZ3Fzgzh0mXJby2unoCFSoAJQtC7x9CyQnI8fJCbYchbOxWL+ZQY9LLLmu1G8fRkt5rcvLyzN7vgxOZmRo6lWoAOsLF5jZbceOAb17Azt2MJ/YWGbmmFgMlC8P1K7NXLsMsK2LVxcMbDAQO27vwOCDg3Fz1E2IhJbfF6QDGRSzIRaLUbNmTbVljx8/xhdffIGvv/4a3333HZydnXHp0iUMGzYMUqlUZ2cqPDwcAwYMwNGjR3H8+HGEhYVh165d6NmzJzIzMzFq1ChMmDBBa7sqVarotc3BwQE3btwAn89HxYoV2X/clEmDCsPPzw+JiYk4fvw4zpw5gz59+iA4OBj79u0rclt9dO3aFYQQHD16FE2bNsXFixexcuVKdn1mZibmz5+vM1mjvocJAHOBUh6DpUuXokuXLpg/fz4WLlwIgMlZMW3aNERERCAgIAAODg5Yvnw5rl69Wqi9mZmZaNy4sdo//0r0JeR0cXEBAKSmpmqVUT7Isba2RqVKlYx6cDF8+HB07NgRR48exalTp7BkyRJERERoDdgYQ0hICIKCgvD69WucPn0aIpGIzZGSmZkJADh69KhWfHAbGxuD9E05D3RharvgipSUFHZQkUKhUCjGo9pX2rJlC3x9fbF582YMGzbMoPtNUQ+eQ0ND8e7dO6xevRpVq1aFjY0NAgICIJVKTbbZxcUFqampOtddvHgRjo6OcHV1NSp0lYeHBxISEnDmzBmcPn0aY8aMwfLly3HhwgW9gzRF0bRpU3h6erL5uQ4cOKAWVtHUPqQqXPjXlD4Vl6SkpEAsFtNBDArlE+RDxIvP3xHzN/+hI5cPbTl9AKx6v1E+hFT+VSgAubxgoENJdjbzAQDl/182NkyicHd35Lx/D67+K7NYv5lBj0ssua7Ubx9G64Nd62BAkm9T9Xg8wM4O+OoroH9/4I8/mOX16qlvsGABMHeuwbat7rQaZx6dQcK7BMw5NwcRHSO4NN8s0IEMygfl+vXrUCgUiIiIYC8+e/bsKXI7Ly8veHl5YfLkyejfvz+2bt2Knj17ws/PD3FxcVoDJkXB5/N1buPo6IhKlSohKipKLddBVFQU/P391cr17dsXffv2xVdffYVOnTohJSUFzs7OanrKkU65XF6oPba2tujVqxd+//13NimmaqJIPz8/JCQkGF1PTebMmYN27drh66+/ZusZGBiIMWPGsGU03/6ztrbWst/Pzw+7d++Gq6urwfEXPT094ejoiLi4OHh5eamt0zXoBQA+Pj6QyWS4evUqAgMDAQDv3r1DQkIC6tSpw5bz8PDA6NGj2aTrGzdu1DmQoasuuggMDISHhwd2796N48ePo3fv3uyDlDp16sDGxgZPnz41OB+GJoaeBzKZDNeuXWPbXkJCAt6/f8++JcpVuzCV2NhYoxKcUygUCkU/fD4f3377LaZMmYIBAwYYdL9p0KABfv31V+Tl5el84B8VFYV169ahc+fOAJik0m/fvi2WnY0aNUJcXJzOddWrV1dLrq3Ex8cHUVFRCA0NVbNN9V4uEonQtWtXdO3aFWPHjkXt2rVx584dnYnJhUKhQffzkJAQ/P7776hcuTL4fL5aQmtT+5CqGOrff/75B4MGDVL7rZxVY0qfiktiY2ONmlFKoVAoRqMxkGGxb7SrvkGt/M7nM0m/ZTJmVkZhGPhSm6lYmt8OHjyIadOmITExEWPHjoWvry+mTp1qcAL5D0VpmllgTiIjI9G2bVukpqaibNmyJeo3Ho+HAwcOoEePHgZpDR48GO/fv8fBgwc5sbU45OTkAODuxVKdehs2MPkxfvlFe4N584Du3Zmk4AZoOYmcsKnbJnTZ2QUr/1mJHrV7oFXVVpzYbi5K/myhfFLUrFkTeXl5+PHHH/Ho0SPs2LEDGzZs0Fs+Ozsb48aNQ2RkJJ48eYKoqChER0ezD3JnzJiBy5cvY9y4cYiJicH9+/dx6NAhjBs3zmQbp0+fju+//x67d+9GQkICZs6ciZiYGEycOBEAsGLFCvzxxx+4e/cu7t27h71798LNzU3nP+6urq4QiUQ4ceIEXr16hbS0NL37DQkJwdGjR7FlyxaEhISorZs3bx62b9+O+fPn47///kN8fDx27dqFOXPmGFW3gIAANGjQAIsXLwYA1KpVC9euXcPJkydx7949zJ07F9HR0WrbVKtWDbdv30ZCQgLevn2LvLw8hISEwMXFBd27d8fFixeRmJiIyMhITJgwAc+ePdO5bz6fj+DgYFy6dMlge2vVqoXu3btjxIgRuHTpEm7duoX//e9/cHd3R/fu3QEAkyZNwsmTJ5GYmIgbN27g/PnzesNBVKtWDZmZmTh79izevn1baFikAQMGYMOGDTh9+rTa8XBwcMC0adMwefJk/Prrr3j48CFu3LiBH3/8Eb/++qtB9TL0PBAKhRg/fjyuXr2K69evY/DgwWjevDk7sGFKuxg0aBBmzZpVqH1Pnz5FTEwMnj59CrlcjpiYGMTExLBvBwPMrJLnz58jODjYoDpTKBQKpWh69+4NgUCAtWvXGnS/GTduHNLT09GvXz9cu3YN9+/fx44dO5CQkACAuY/u2LED8fHxuHr1KkJCQor9pljHjh1x5coVgwYSlEyfPh3btm3D+vXrcf/+faxYsQJ//vknpk2bBoBJXr1582bExsbi0aNH+O233yASidQSn6tSrVo1nD17Fi9fvtQ7OwRg+lY3btzAd999h6+++kpt5iQXfUhD/bt3715s2bIF9+7dQ1hYGP799192P6b0qQ4cOIDatWsXaltmZiZ7/waAxMRE9t6uysWLF4sdIpVCoVAKRfngMn9Ag8fjmfyG9ODBg9UebhZHSwtdMzIAVOvSBbymTcETi2EXEID6/fphk64HphwOZERERMDJyYl98AgU1DUrKwuOjo5Ys2YNY1+1ali1alWBvdWqsWWVn8qVK6vpa/qNx+MZ/RB41KhR+Oqrr5CUlIQFCxZ80LfejcGUNrJt2zZ2O2UUj759++Lp06ectjlO2y/H6LJN6Rddz1v27t0LHo+HatWqGazHpW2WglAoNHk2scF6jo7Azz8DP/3E/Pb3B4YMKVg/fDgzg8xA2zrX6oyhDYeCgGDIoSGQSCWc2W8O6EAG5YPi6+uLFStW4Pvvv0e9evXw+++/Y8mSJXrLCwQCvHv3DoMGDYKXlxf69OmDzz//HPPnzwfAvIl44cIF3Lt3D61atUKjRo0wb948VKpUyWQbJ0yYgClTpmDq1KmoX78+Tpw4gcOHD6NWrVoAmAfZy5YtQ5MmTdC0aVM8fvwYx44d0zmybGVlhTVr1uDnn39GpUqV2IfvumjXrh2cnZ2RkJCAAQMGqK3r2LEj/vrrL5w6dQpNmzZF8+bNsXLlSr3/4BfG5MmTsWnTJiQlJWHUqFHo1asX+vbti2bNmuHdu3dqszMAYMSIEfD29kaTJk1Qvnx5REVFwc7ODn///TeqVKmCXr16wcfHB8OGDUNOTk6hbxMOHz4cu3btYkfQDWHr1q1o3LgxvvjiCwQEBIAQgmPHjrEXYLlcjrFjx8LHxwedOnWCl5cX1q1bp1MrMDAQo0ePRt++fVG+fHksW7ZM735DQkIQFxcHd3d3rZwpCxcuxNy5c7FkyRJ2v0ePHkX16tUNqpOh54GdnR1mzJiBAQMGoEWLFrC3t8fu3bvZ9aa0i6dPnyI5OblQ++bNm4dGjRohLCwMmZmZaNSoERo1aoRr166xZf744w989tlnJrVBCoVCoejGysoK48aNw7JlyyCRSIq835QrVw7nzp1DZmYmgoKC0LhxY2zcuJG9R27evBmpqanw8/PDwIEDMWHCBLi6uhbLxs8//xxWVlY4c+aMwdv06NEDq1evxg8//IC6devi559/xtatW9GmTRsAQNmyZbFx40a0aNECDRo0wJkzZ3DkyBGUK1dOp15ERAROnz4NDw+PQmcT1KxZE/7+/rh9+7bWSyJc9CEN9e/8+fOxa9cuNGjQANu3b8cff/zBzkYxpU+VlpbGDlbp49q1a+z9G2ByzinrqOT58+e4fPkyhqj+80uhUChcozEjw2LJv3cSle8AAB4PC0aNQvLt24j94w/87/PPMeK773A8Kkp9ew4HMpS5Gv/880+tdfv27YNUKsX//vc/vdsvWLAAycnJ7OfmzZuc2QYwg+WvX79Gx44dUalSJaPCSX4sODo6Ijk5Gc+fP8f+/fuRkJCA3r17l7RZJY5YLMbr169x5coVteWbN282ODRnaYYQAkLIh9EbOxZ48wa4ehXYsoXJ51OmDBAdDeTnoTNUa0XHFfBw9MDD1IeYdbbwF19LHE7Si1MoFIoBKBQK0rRpU7Jz586SNoVSDHJzc0mVKlXIpUuXStoUCoVCoZQAP/30E/nss89K2gxKMfnmm2/IiBEjStoMCoViBtLS0ggAkpaWprUuOzubxMXFkezsbIP1UlNTTTcmPp6Q6GhCXr4khBAik8mITCYzSSo0NJR0796d/a2qFRkZSZo2bUqsra2Jm5sbmTFjBsnLy2PLpqenkwEDBhA7Ozvi5uZGVqxYQYKCgsjEiROVBQiJjiaKW7fU9lm1cmWycvJkQh4+ZOoRHU2cy5QhkwcMYH+nnjtHhg0dSlxcXIiDgwNp27YtiYmJUfPbwoULSfny5Ym9vT0ZNmwYmTFjBvH19dVb1169epH27dtr1TUoKIj07du3wL6qVcnKlSv1/taF5jEAQA4cOEAIISQxMZEAIPv37ydt2rQhIpGINGjQgFy+fJkQQsj58+cJmPEe9nPmzBmyefNmUqZMGVZT81gRQsjEiRNJUFAQ+1sul5PFixeTatWqEVtbW9KgQQOyd+9e1m/KfZ05c4Y0btyYiEQiEhAQQO7evaume/jwYdKkSRNiY2NDypUrR3r06MGuk0gkZPLkyaRSpUrEzs6O+Pv7k/Pnzxfqn61bt6rVhRBC1qxZQwCQlJQU1ncHDx4kjRo1IjY2NqR69eokPDxcrc0BIBs2bCBdunQhIpGI1K5dm1y+fJncv3+fBAUFETs7O9K8eXPy4MEDtX2tW7eO1KhRgwiFQuLl5UW2b9/Oruvfvz/p06ePWnmpVErKlStHfv31V5KamqrXr6ocPXqU1KpVi9ja2pI2bdqQrVu3EgCs73Wdp0q/jBs3jgwfPpxdnpSURGxsbMjMmTNJ1apVDa4LIYTcu3ePtGrVitjY2BAfHx9y6tQptfZICCFPnz4lvXv3JmXKlCFOTk6ka9euaj7T1dZUMeSad/jwYb3rjCEtLU3ndfeD6W3cSAhAiEjEXLPi4gj54QdCsrKK1Dr14BRBOAjCQc49OmfQ7rj0m757liYWPiROoVBKEzweD7/88gtkMllJm0IpBk+fPsW3336rNVOFQqFQKJ8Go0aNQuvWrZGRkVHSplCKgaurKxYuXFjSZlAoFAuAEAKJVKL/k1fIuqI+ihxIZNmQyLIgkUqQlZeFrDzmOynmm8vKEDPPnz9H586d0bRpU9y6dQvr16/H5s2bsWjRIrbslClTEBUVhcOHD+P06dO4ePEibty4USBmbw9SvjyIu7vunaWkQKFQYP/Fi0hNT4e1VUHK2d4zZ+L1mzc4fvw4rl+/Dj8/P7Rv354Nf/j777/ju+++w/fff4/r16+jSpUqWL9+faF1GzZsGM6dO4cnT56wdU1MTMTff/+NYcOGmegxsFpFheaZPXs2pk2bhpiYGHh5eaF///6QyWQIDAxkZwXu378fycnJJv9fuGTJEmzfvh0bNmzAf//9h8mTJ+N///sfojRmu8yePRsRERG4du0arKysMHToUHbd0aNH0bNnT3Tu3Bk3b97E2bNn1fKbTpgwAVevXsWuXbtw+/Zt9O7dG506dcL9+/cNtvP169c4cOAABAIBrKyswOPxcPHiRQwaNAgTJ05EXFwcfv75Z2zbtg3fffed2rYLFy7EoEGDEBMTg9q1a2PAgAEYNWoUZs2ahX///RcA1MJaHjhwABMnTsTUqVMRGxuLUaNGYciQITh//jwAJnLEkSNH1MI+nzx5EllZWejZs2ehfr1w4QIAJqdXr1690LXr/9u787Coqj4O4N9hG3YQFUEFFwzEnU1DXhUUxVSM1zfNQkXELXNPRU3FJbVyL01KDdI0l9ddUXOjlCxXTAt3UDOXXNiGbWDu+4fv3BgWheHCTPL9PA9Pzp1zf/d3fjMDPffMOScYiYmJGDp0KKZOnaqR94veI0OGDMHWrVvFpbpjY2PRvXt31KlTR6Nd4b78+uuvGD58uEZfVCoV+vTpAxMTE/zyyy+Ijo5GZGSkRgylUomgoCBYWVnhxIkTSEhIgKWlJXr27Im8l+1bowNVsrTUi0REAAEBQHY24OICNGsGTJoETJ780lhdXbpihNcIAMCQPUOQkaun/58vydAJERERERERERHpXHlnZGTmZorfxK3Kn8zczHL1q+g3r5VKpaBUKoXp06cLbm5ugkqlEp9btWqVYGlpKRQUFAjp6emCsbGxxrfSU1NTBXNz879nZBSKV1gDJyfBxNhYsDAzE4wMDQUAgp2NjXB9xw5BOHNGOLFmjWBtYSHk5ORonOfi4iLOjGjXrp3w/vvvazzv5+f3whkZ+fn5Qr169YSoqCgxtw8//FBwdnYWCgoK/s6vhBkZJiYmgoWFhfizYsUKjdhF+4kSZmSsXbtWfP63334TAAhJSUmCIDyfoQNAnNmgVCqFtWvXlmtGRk5OjmBubi7O9FCLiIgQ/vOf/wiCoDkjQ23//v0CAPH96+vrK4SGhpZYw9u3bwuGhobC7du3NY536dJFmDZtWonnCIIgzk6wsLAQzM3NxZknY8eOFWvXpUsXYcGCBRrnbdiwQXB0dBQfAxBmzJghPj516pQAQFi3bp0gCM/r9u233wqmpqZim/bt2xebLdm3b1+hR48e4jm1atUqNktDPUvnwYMHpdb1nXfeEQRBEKZNmyY0a9ZM4/nIyEiNGRklfRYKz1Rp06aN8M033wgqlUpwcXERdu/eLSxbtkxjRkbhvqjjFe7LoUOHBCMjI+HevXviOQcOHNB4P27YsKHYZ1uhUAhmZmbCoUOHBEHQrxkZT58+FZ4+fSpJLK3jXb/+fFZGkZ/0vXtfGis9J11ouLyhgNkQRuwd8dJLcUYGERERERERERHRSxgYGMDAwABJSUnw9fXV+Aa5n58fMjMz8ccff+DWrVtQKpUa39S3sbGBm5ub+HjBggWwtbWFra0tLC0tcefOnedPyGSYPHAgEjduxLHVq9GuTRssmzkTTZycAAAXr11DZnY2atasCUtLS/EnOTkZycnJAICrV69qXBuAxuMTJ05onLtx40YYGhoiLCwMsbGx4syVDRs2IDw8vMT9OQubPHkyEhMTxZ9BgwYBAEaOHAlLS0uxny/SqlUr8d+Ojo4Ans9MKImBgUG5N1++ceMGsrKy0LVrV42+r1+/HikpKWXOJTExEV26dCnxGpcuXUJBQQGaNWumcY0ffvgBN2/eBACN4yNHjhTPtbKyQmJiIs6ePYslS5bA09MT8+fPF99zFy9exNy5czXOHzZsGO7fvy/OVCiau3rGQsuWLcW6OTg4ICcnB+np6QCApKSkYjNc/Pz8kJSUBOD5fmr9+vXDxo0bAQAKhQK7d+8W9wK7detWqXVV9zkpKQnt2rXTuIavr6/G48KfhcJ1URsyZAhiYmLwww8/QKFQoEePHsXaFO6Lum6F+5KUlAQnJyeN/cmK5nHx4kXcuHEDVlZWYl/s7e2Rk5Mj9kefWFhYwMLCQrfxmjQBYmP/fuzpCQCwHDsWL4tkJbfC172/BgB8ee5LfH/z+/JduwoYvbwJERERERERERG9isyNzZE5LbPU51PTUmFrYyvJtdTLDBsZGcHc2LxCsVQqlRQpAXh+k79Pnz4AnudW+OZqLRsbNHFyQhMnJ2xbswYtAwPh7eODZs2bI1OphKODA+L/v2xPYWW9ue/t7Y3ExETxsfqG95AhQ7Bw4UIcO3YMSqUSd+/eRXh4+Evj1apVC02aNCl2fO7cuZg0aVKZlnouvASNuh+l1VulUhVbJszAwKDYMaVSKf5bvTTS/v37Ua/Icl45OTllzsXMzKzUPmRmZsLQ0BC//PIL5EU2Y7e0tAQAjbpbW1tr5K+uobu7O27evIn33nsPMTExYuw5c+aI75nCTE1NX5i7+ljhepbnvRwaGopOnTrh0aNHOHz4MMzMzNC9e3cAzwc2gJLrWrQGL3L27FkAzz8LhetSOIcpU6Zg9uzZGDhwIIyMXnx7WdvPamZmJry8vMSBG+Dv3yHqQS19oq6/iYmJbuOFhT3/AYD0dKBFC8iSk6GaOhX48svnxx8/BubOBd55Byg0gBTQKABj2o7B56c/x9A9Q3HpvUuwMbWRojuS4EAGEREREREREVE1JZPJYGFS+nd1lcbKFz5fHiqj5zc0XzaroCzUMdzd3bF9+3YIgiDeLE5ISICVlRXq16+PGjVqwNjYGGfOnIGzszMAIC0tDdeuXUPHjh0BAHZ2duIsBY3cigxGODVsiLfffhvTlizB7t274dmjBx58/jmMjIzQsGFDjbapqakAADc3N5w5c0acGQEAZ86cEf9tZmZW4sCDi4sLOnXqhK+//hoqlQpdunRBgwYNyl+o/7O3t4e9vb2kA0BAyTMyateujcuXL2scS0xMFG/iN2vWDHK5HHfu3EGnTp002qnrVhatWrXC0aNHSxzg8fDwQEFBAR4/flzsGmol1b0kU6dOhYuLC8aNGwdPT094enri6tWrZT6/JCXVzd3dHQkJCQhT34TG8/dys2bNxMft27eHk5MTtmzZggMHDqBv375iXd3c3Eqta+Fr7NmzR+PYzz//rPHY1dVVzLEkdnZ26N27N7Zu3Yro6OhSr6PuizpO4b64u7vj7t27uH//vjgoUTQPT09PbNmyBfb29uKAivr9K8XvEKlJORtDsnjW1sCaNUD37pCvWQMMGABERwObNj1/fuNG4MoVoHZt8ZSFXRYi7nocbj67iXEHxyE2JLbieUiEAxlERERERERERFTpKnoTMi0tTfwWvfqb2cOHD8fy5csxZswYjB49GlevXkVUVBQmTpwIAwMDWFlZISwsDJMnT4adnR3s7e0RFRVV7EZymXIzNsa4cePQokULnD17FoGBgfD19UVISAg+/fRTuLq64s8//8T+/fsRGBiIgIAAjBkzBsOGDYO3tzfat2+PLVu24Ndff0Xjxo1f2t+IiAgMGzYMALBu3TqtalaU1DeCS5qR0blzZyxatAjr16+Hr68vvv32W1y+fBkeHh4Ani/dNGnSJEyYMAEqlQr/+te/kJaWhoSEBBgZGeG9994r07WjoqLQpUsXuLi4oH///sjPz0dcXBwiIyPFTcoHDx6MJUuWwMPDA3/99ReOHj2KVq1aoWfPnmXuo5OTE/79738jKioKu3fvxqxZs9CrVy84OzvjrbfeEpebunz5ssYm8+Wt2+TJk9GvXz94eHggMDAQe/fuxY4dO3DkyBGNdu+++y6io6Nx7do1cfNs4MV1tba2RlhYGEaOHIklS5Zg8uTJGDp0KM6dO4fYwksRoWzvkdjYWHzxxReoWbNmic8X7ou/vz/27dun0ZfAwEC4uroiLCwMixYtQnp6Oj788EONGKGhoVi0aBHefPNNzJ07F/Xr18etW7ewc+dOTJ06FfXr139xkauY3szIKCooCLkDBkD+7bdAjx5Aoc3i8fQpMGoUsHWrOHBrYWKBb0K+QcfYjvjm4jfo5doLbzV7q2I5SET/hq+IiIiIiIiIiOiVo14rX1vx8fHw8PCAh4cHfHx84OPjg3nz5iEuLg6nT59G69atMXLkSERERGDGjBnieUuXLoWvry969eqFwMBA+Pn5wd3dXWMZoFJzs7cH5HKgVi3A2hrNmjVDt27dMGvWLMhkMsTFxaFjx44IDw+Hq6sr+vfvj9u3b6P2/7/hHBoaimnTpmHSpEnw9PREcnIyBg8erHHt0vznP/+BXC6Hubk5/v3vf2tdt8Iq+hqUFK/ozIKgoCDMnDkTU6ZMgY+PDzIyMjRmpADAvHnzMHPmTCxcuBDu7u7o3r079u/fL86aKQt/f39s27YNe/bsQZs2bdC5c2ecPn1afD4mJgYDBw7EBx98ADc3N4SEhGjMzCmPCRMmIC4uDmfPnkVQUBD27duH77//Hj4+Pnj99dexbNmycs2YKaluISEhWLFiBRYvXozmzZvjyy+/RExMDPz9/TXahYaG4vfff0e9evWK7alRWl0bNWoEAHB2dsb27duxa9cutG7dGtHR0ViwYEGx3F72HjEzMyt1EKNoX1q3bo21a9dq9MXAwAA7d+5EdnY22rZti6FDh2L+/PkaMczNzfHjjz/C2dkZffr0gbu7O4YPH47c3NwSl7zSNTMzsxcud6bLeMLixRDq1dMcxJgyBTAyAv77X2DLFo32fs5+mOo3FQAwYt8I/JnxpyR5VJRMKDr8R0RERERERERE/0jp6emwsbFBWlpasZt9OTk5SE5ORqNGjcp0Ix14vtTPyzaHLqvCe2ToMpZCoUC9evWwZMkSRERESJ4b8OK6de3aFQ4ODtiwYUOZYulL3aoinr6+36SOJ3VugHS1e5XqVpbfeXv37kVwcHCFc0tLSwMA2NhIs6eElPHS0tJgdPQoLN5+GwgKAvbsAQwMgDlzgNmz/27o7AxcvAjY2iKvIA++63xx/v55dHPphgOhB2Ag+3uAS6q6vehvVlGckUFERERERERERJVOJpOVeRNsKWNduHAB3333HW7evInz588jNDQUAPDmm29WSm6FZWVlYenSpfjtt99w5coVREVF4ciRIxr7ILyMruqmi3hS0ue+sm66jyU1Q0NDGBoa6mU8Q0NDCN26AX/+Ceza9XwQAwCmTwdatPi74Z07wNixAAATQxNs7LMRZkZm+P7m91h1epUkuVQEBzKIiIiIiIiIiOiVpl7iJjAwEAqFAidOnECtWrUq/bqFl5/y8vLC3r17sX37dgQGBlb6tYmINNSu/Xw5KTVjY2DnTqB587+PbdgAbN8OAGhaqykWdV0EAJhyZAp+/+v3qsy2GG72TURERERERERElU7K1c3LE8vDwwPnzp2TLF55mJmZFdusubx0VTddxJOSPveVddN9LKkVFBTobbwXxmrSBLh8+fm/p08HFi4ERowA2rcHHB0xymcU9l3fh4M3DmLAjgH4eejPMDGUZkPz8uKMDCIiIiIiIiKiSvDjjz8iODgYdevWhUwmw65du156Tnx8PDw9PSGXy9GkSRPExsZWep5VRcqNpitj02op40mJddOOPveVddN9LKnJ5XLI5XK9jFfmWLNnA23aAE+eAOHhwPjxkBkYIC7iOCb8aoELDy4g6niUJDlpQz9feSIiIiIiIiKifziFQoHWrVtj1aqyrS2enJyMnj17IiAgAImJiRg/fjyGDh2KQ4cOVXKmVUOlUkGlUuldrMqIJyXWTTv63FfWTfexpJadnY3s7Gy9jFfmWCYmz5eWMjEBDh0CVqwAAMhyc7F0hwJdbwCfJHyCE7dPSJJXeXFpKSIiIiIiIiKiSvDGG2/gjTfeKHP76OhoNGrUCEuWLAEAuLu74+TJk1i2bBmCgoIqK80qI/W3vKWkr9/yBlg3belzX1k33ceSmoWFhd7GK1esFi2ABQuASZOKPbV1vxmaDM3G1HXvYKzHYsnyKysOZBARERERERER6YFTp04V2wQ6KCgI48ePL/Wc3Nxc5Obmio/T09MrK70KU3+TWoqbkVLGqox4UmLdtKPPfWXddB9LagqFAgBgYiLN/hFSxit3rAkTgMePARsbIDISyMoCfHxgm5SEHzaZoN7jezjffBzQtRdgaVnh/MqKAxlERERERERERHrgwYMHqFOnjsaxOnXqID09HdnZ2TAzMyt2zsKFCzFnzpxixw8cOABzc3ONY0ZGRrC3t0d6ejpycnLKnFdqamqZ29LfWDftsG7aY+005eXlISsrC8ePH0d+fn6JbVQqFfbu3VvFmf0DtG///L/79gEArEeMQIdJk9D8Xh4AwOavZ9h8cBcs5DYVukxWVlaZ23Igg4iIiIiIiIjoH2ratGmYOHGi+Dg9PR1OTk544403YG1trdE2JycHycnJsLa2hqmpaZnip6amwtbWVpJc1TcSjYwqfjtKyliVEY91046+1k3qeFLnBkhXu1epbjk5OTA3N0dAQECpv/P27t2L4ODgCuf27NkzAECNGjUqHEvqeJLFUiqByZOhtDDDw+mfov9bAyqcW3lmEXIgg4iIiIiIiIhIDzg4OODhw4caxx4+fAhra+sSZ2MAgFwuh1wur4r0Kkyf18rXx6Vq1Kpj3WQyGXbu3ImQkJAytR88eDBSU1Oxa9euSstNn18HKbFu2inr4LAu4kkWa+JEoGZNGDdvjoIif6uqgv6++kRERERERERE1Yivry+OHj2qcezw4cPw9fXVUUbSEgQBgiBode7gwYM1bmpXJFZJSorXsGFDyGQyyGQymJubo2XLlli7dq1k1yxNSkqKeF2ZTAZTU1O4urrio48+qnCfK1q32NhYyGQyuLu7F4u3bds2yGQyNGzYsEI5SqUq3iP6EEtqrJt2lEollEqlXsaTLJaBARAeDrRtW/FY2lxeJ1clIiIiIiIiInrFZWZmIjExEYmJiQCA5ORkJCYm4s6dOwCeLws1aNAgsf3IkSNx69YtTJkyBVeuXMEXX3yBrVu3YsKECbpInwDMnTsX9+/fx+XLlzFgwAAMGzYMBw4cqJJrHzlyBPfv38eVK1cQFRWF+fPn4+uvv66Sa7+IhYUFHj16hFOnTmkcX7duHZydnXWUFZFuGRgYSD77RKp4UuemK//8HhARERERERER6aGzZ8/Cw8MDHh4eAICJEyfCw8MDs2bNAgDcv39fHNQAgEaNGmH//v04fPgwWrdujSVLlmDt2rUICgrSSf7/FD/88APatm0LuVwOR0dHTJ06VWNj34yMDISGhsLCwgKOjo5YtmwZ/P39MX78+JfGtrKygoODAxo3bozIyEjY2dnh8OHD4vOpqakYOnQoateuDWtra3Tu3BkXL17UiPHRRx/B3t4eVlZWGDp0KKZOnYo2bdq89No1a9aEg4MDGjRogHfffRd+fn44f/68+PyZM2fQtWtX1KpVCzY2NujUqZPG84IgYPbs2XB2doZcLkfdunU1+pybm4tJkyahXr16sLCwQLt27RAfH//SvIyMjPDuu+9qDKr88ccfiI+Px7vvvlus/erVq+Hi4gITExO4ublhw4YNGs9fv34dHTt2hKmpKV5//XWN+qrdvXsX/fr1g62tLezs7PDmm28iJSXlpbkSVRX1DCp9jCd1brrCgQwiIiIiIiIiokrg7+8vLoVS+Cc2NhbA82V6it449vf3x4ULF5Cbm4ubN29i8ODBlZukIAAKRZX8CJmZEDIznz+WaImke/fuoUePHvDx8cHFixexevVqrFu3Dh999JHYduLEiUhISMCePXtw+PBhnDhxQuOGf+F4pVGpVNi+fTuePXsGExMT8Xjfvn3x6NEjHDhwAOfOnYOnpye6dOkibq67ceNGzJ8/H5988gnOnTsHZ2dnrF69utx9PXPmDM6dO4d27dqJxzMyMhAWFoaTJ0/i559/xmuvvYYePXogIyMDALB9+3YsW7YMX375Ja5fv45du3ahefPmYj9Hjx6NU6dOYfPmzfj111/Rt29fdO/eHdevX39pTkOGDMHWrVuhUCjE93T37t1Rp04djXY7d+7EuHHj8MEHH+Dy5csYMWIEwsPDcfz4cbGuffr0gYmJCX755RcsWbIEkZGRGjGUSiWCgoJgZWWFEydOICEhAZaWlujevTvy8vJeWDcukVR+rJt2qsXSUjrGzb6JiIiIiIiIiKqrrCzA0rLUp20lvJTGTajMTMDCQutY6mVSvvjiCzg5OWHlypWQyWRo2rQp/vzzT0RGRmLWrFlQKBT45ptvsGnTJnTp0gUAEBMTg7p165YYr6jIyEjMmDEDubm5yM/Ph52dHYYOHQoAOHnyJE6fPo1Hjx6JG64vXrwYu3btwu7duzF+/Hh8/vnniIiIQHh4OABg1qxZ+P7775GZmfnSPrZv3x4GBgbIy8uDUqnE8OHDNZYi69y5s0b7r776Cra2tvjhhx/Qq1cv3LlzBw4ODggMDISxsTGcnZ3h7e0NALhz5w5iYmJw584dsRaTJk3CwYMHERMTgwULFrwwNw8PDzRu3Bg7duzAwIEDERsbi6VLl+LWrVsa7RYvXozBgwdj1KhRAJ4PKv38889YvHgxAgICcOTIEVy5cgWHDh1C3bp10aBBAyxYsABvvPGGGGPLli1QqVRYu3at+K3ymJgY2NraIj4+Ht26dSsxR25arR3WTTvVYrNvHdPfV5+IiIiIiIiIiKgEKpUKKpUKSUlJ8PX11Vg2xc/PD5mZmfjjjz9w69YtKJVKtC20Oa2NjQ3c3NzExwsWLIC1tTWsra1haWmpsdzX5MmTkZiYiGPHjqFdu3ZYtmwZmjRpAgC4ePEiMjMzUbNmTVhaWoo/ycnJSE5OBgBcvXpV49oANB6fOHFC49yNGzeKz23ZsgWJiYk4d+4cvvvuO+zevRtTp04Vn3/48CGGDRuG1157DTY2NrC2tkZmZqaYf9++fZGdnY3GjRtj2LBh2LlzJ/Ly8qBSqXDp0iUUFBTA1dVV4/o//PADbt68CQAax0eOHFnsNRgyZIg4q0ihUKBHjx7F2iQlJcHPz0/jmJ+fH5KSksTnnZycNAaWim5uf/HiRdy4cQNWVlZiPnZ2dsjJyRFzLYn6PSIVKeNJnZuUWDftZGdnIzs7Wy/jSZ2brnBGBhERERERERFRdWVu/nx2RClSU1Nha2sryaXUNyANDAyeX7cCpPxm9siRI/HWW2+JcQvfVK9VqxaaNGmCJk2aYNu2bWjZsiW8vb3RrFkzZGZmwtHRscR9Jcq6Hr23t7e4GTwA1KlTB0+ePAEAODk5oUmTJlCpVGjevDlSUlIwc+ZMzJ49G6ampggLC8OTJ0+wYsUKNGjQAHK5HL6+vuJyS05OTrh69SqOHDmCw4cPY9SoUWjUqBGOHz+OzMxMGBoa4ty5czA0NNTIyfL/M3QK52VtbV0s99DQUEyZMgXz5s3DwIEDYWRUObcZMzMz4eXlpTHIo1a7du1Sz+PMAu2wbtqxqMAMs8qOJ3VuusKBDCIiIiIiIiKi6kome/EST0plhZaAKkz1/w24DSS44a0eFHF3d8f27dshCII4eJCQkAArKyvUr18fNWrUgLGxMc6cOQNnZ2cAQFpaGq5du4aOHTsCAOzs7MQb9S+6Ge/k5IS3334b06ZNw+7du+Hp6YkHDx7AyMgIDRs21GibmpoKAHBzc8OZM2c0loQ6c+aM+G8zMzNxhoeaeiCjaF8NDQ2Rn5+PvLw8mJqaIiEhAV988YU4E+Lu3bt4/PixxrlmZmYIDg5GcHAw3n//fTRt2hQXL16Eh4cHCgoK8OjRI3To0KHE/hbNqyg7OzsEBwdj27ZtiI6OLrGNu7s7EhISEBYWJh5LSEhAs2bNxOfv3r2L+/fvw9HREQDw888/a8Tw9PTEli1bYG9vX+KASmk0Bs4kIGU8qXOTEuumHYVCAQAae+joSzypc9MVDmQQEREREREREVGlq+jNx7S0NHGWgPqG5vDhw7F8+XKMGTMGo0ePxtWrVxEVFYWJEyfCwMAAVlZWCAsLw+TJk2FnZwd7e3tERUXBwMBAY9ZEWXMbN24cWrRogbNnzyIwMBC+vr4ICQnBp59+CldXV/z555/Yv38/AgMDERAQgDFjxmDYsGHw9vZG+/btsWXLFvz6669o3LjxS6/15MkTPHjwAHl5ebh06RJWrFiBgIAA8Wb+a6+9hg0bNsDb2xvp6emYPHkyzMzMxPNjY2NRUFCAdu3awdzcHN9++y3MzMzQqFEj1K5dG6GhoRg0aBCWLFkCDw8P/PXXXzh69ChatWqFnj17lqkeMTExWLVqVakzIyZPnox+/frBw8MDgYGB2Lt3L3bs2IEjR44AAAIDA+Hq6oqwsDAsWrQI9+7dw6xZszRihIaGYtGiRXjzzTcxd+5c1K9fH7dv38aOHTswZcoU1K9fv8Rrc2aBdlg37XBGRuXT31efiIiIiIiIiIheGRVd3z4+Ph4eHh7w8PCAl5cXvLy8MG/ePMTFxeH06dNo3bo1Ro4ciYiICMyYMUM8b+nSpfD19UWvXr0QGBgIPz8/uLu7a2yAW9bcmjVrhm7dumHWrFmQyWSIi4tDx44dER4eDldXV/Tv3x+3b98Wb+yHhoZi2rRpmDRpEjw9PZGcnIzBgweXafPdwMBAODo6onHjxhg5ciR69OiBLVu2iM+vW7cOz549g6enJwYOHIixY8fC3t5efN7W1hZr1qyBn58fWrVqhSNHjmDXrl2oUaMGgOeDEIMGDcIHH3wANzc3hISEaMxcKQu5XC7GK0lISAhWrFiBxYsXo3nz5vjyyy8RExMDf39/AM9vTO/cuRPZ2dlo27Ytxo0bh/nz52vEMDc3x48//ghnZ2f06dMH7u7uiIiIQE5OzgtnaHCvB+2wbtpRKBTizAd9iyd1broiEwRB0HUSRERERERERERUcenp6bCxsUFaWlqxm7w5OTlITk5Go0aNynQjHajEPTJ0GEuhUKBevXpYsmQJIiIiJM8NeHHdunbtCgcHB2zYsKFMsfSlblURT1/fb1LHq4wlkqSq3atUt7L8ztu7dy+Cg4MrnJt6M+3Cs6L0JZ7UuQHS1e1Ff7OK4tJSRERERERERERU6aT8Lm15Yl24cAFXrlxB27ZtkZaWhrlz5wIA3nzzzUrJrbCsrCxER0cjKCgIhoaG+O6778TNt8tKV3XTRTwp6XNfWTfdx5KaUqkEIN1ggZTxpM5NVziQQUREREREREREr7TFixfj6tWrMDExgZeXF06cOIFatWpV+nXVy0/Nnz8fOTk5cHNzw/bt2xEYGFjp1yaiqlN4zx19iyd1brrCgQwiIiIiIiIiInpleXh44Ny5czq5tpmZmbixNRG9ugwNDfU2ntS56Qo3+yYiIiIiIiIiokonCIJkS8NIGasy4kmJddOOPveVddN9LKnl5eUhLy9PL+NJnZuucEYGERERERERERFVOik3NpYyVmXEkxLrph197ivrpvtYUpN6/wkp4/3T98ZQ40AGEREREREREVE1oqtvNKtUKgDS3IyUMlZlxJMS66Ydfe4r61Y1saryd11WVhYAQC6X6108qXPTFQ5kEBERERERERFVA8bGxgCe39TSxTd09fmb2fp4Q1mNddOOPveVdauaWOob+OrffZXJwsJCb+NJnZuucCCDiIiIiIiIiKgaMDQ0hK2tLR49egQAMDc3h0wme+E5eXl5yMnJkeT6+fn5AAAjo4rfjpIyVmXEY920o691kzqe1LkB0tXuVaibIAjIysrCo0ePYGtrWyWbXSsUCgCAiYmJ3sWTOjdd4UAGEREREREREVE14eDgAADiYMbLZGVlwdzcXJJrq5d5edngSVXHqox4rJt29LVuUseTOjdAutq9SnWztbUVf+dVNqnet5URT+rcdIUDGURERERERERE1YRMJoOjoyPs7e2hVCpf2v748eMICAiQ5Nrp6ekAAGtra72KVRnxWDft6GvdpI4ndW6AdLV7VepmbGxcJTMx1LKzswFItw+FlPGkzk1XOJBBRERERERERFTNGBoalukmX35+PkxNTSW5pnqjXiniSRmrMuKxbtrR17pJHU/q3ADpalfd6iYVqZdtkjLeP31JKTUOZBARERERERERUaUrKCjQy1iVEU9KrJt29LmvrJvuY0mNdat8HMggIiIiIiIiIqJKp17fXt9iVUY8KbFu2tHnvrJuuo8lNdat8nEgg4iIiIiIiIjoFaNeE10mk8HQ0BB5eXkwMzNDVlYWLCwsoFAoYG5ujuzsbJiYmKCgoACCIMDY2Bg5OTliG0EQ8OzZM5iZmSEnJwfGxsYQBAEqlapYW/V/zczMkJubKy5dVVBQALlcLm5G/OzZM7GtqakplEolDAwMIJPJoFQqYWpqiuzs7GJx1W1lMhny8/OhVCrFuOXpU+E81X3Ky8vTqk+l5SkIAjIzM8vVp9JeJwMDA+Tk5MDIyKhcfSrpdSr8GpS3TyW9Ti96TbV57wmCgLy8vHL1qbTXSalUoqCgACYmJuXqU2ltc3NzIZPJkJWVpfXnSf1fmUwm5qnt56lonoIgIDs7W6vPU9HXSf2aavt5Ktynkt4j2r73lEol8vPzX/qalve9l52drdXnqehrmpeXBwMDA60/T4XbGhoaIisrC8bGxlp/nkr73Ff0d3l2drb4t6Giv8uzsrLK/HeNAxlERERERERERP9wq1atwqpVq5Cfnw8AyMjIKHbzS6lUIisrCwUFBVAoFMjPzy/15pe6TVZWFtLT06FUKku9+aVuq/6vUqks8ebXkydPoFAoxBvyCoVCzKvwza+8vDxkZ2cXi6tuK5PJxOsYGBiUu0+F81T3KS0tDYIgQBCEcvWptDzVdStPn170OuXk5EAQhHL1qaTXqfBrUN4+lfQ6veg11ea9p65befpU2uuUkZEhLqlTnj6V1vbp06eQyWSwtbXV+vNUOE/14Jm2n6eieRb+rJb381T4dSr8mmr7eSrcp5LeI9q+99SvqUwmq9DnqXCf1HXT5vNU0rVtbW21/jwVbqv+3Kufr8jv8qKf+4r+Ls/OzhbrVtHf5eqBjLLMGpEJr8rcEiIiIiIiIiKiau6PP/6Ak5OTrtMgIiIqs7t376J+/fovbMOBDCIiIiIiIiKiV4RKpcKff/4JKysryGSyCsVKT0+Hk5MT7t69C2tra0ny8/HxwZkzZ/QulpTxWDft6HvdpI4nZSypa8e6aYd1Kz9BEJCRkYG6deuKy3KVhktLERERERERERG9IgwMDF76rdbysra2luzGsqGhoV7Gqox4rJt29LVuUseTOjdAutqxbtph3bRjY2NTpnYvHuYgIiIiIiIiIiKSyPvvv6+XsSojnpRYN+3oc19ZN93HkhrrVrm4tBQRERERERERERWTnp4OGxsbpKWlSf5N3lcZ66Yd1k17rJ12WDft6KpunJFBRERERERERETFyOVyREVFQS6X6zqVfxTWTTusm/ZYO+2wbtrRVd04I4OIiIiIiIiIiIiIiPQWZ2QQEREREREREREREZHe4kAGERERERERERERERHpLQ5kEBERERERERERERGR3uJABhERERERERFRNbVq1So0bNgQpqamaNeuHU6fPv3C9tu2bUPTpk1hamqKli1bIi4urooy1S/lqduaNWvQoUMH1KhRAzVq1EBgYOBL6/yqKu/7TW3z5s2QyWQICQmp3AT1VHnrlpqaivfffx+Ojo6Qy+VwdXXlZ7WMtVu+fDnc3NxgZmYGJycnTJgwATk5OVWUre79+OOPCA4ORt26dSGTybBr166XnhMfHw9PT0/I5XI0adIEsbGxlZIbBzKIiIiIiIiIiKqhLVu2YOLEiYiKisL58+fRunVrBAUF4dGjRyW2/+mnn/DOO+8gIiICFy5cQEhICEJCQnD58uUqzly3ylu3+Ph4vPPOOzh+/DhOnToFJycndOvWDffu3avizHWrvHVTS0lJwaRJk9ChQ4cqylS/lLdueXl56Nq1K1JSUvDf//4XV69exZo1a1CvXr0qzlz3ylu7TZs2YerUqYiKikJSUhLWrVuHLVu2YPr06VWcue4oFAq0bt0aq1atKlP75ORk9OzZEwEBAUhMTMT48eMxdOhQHDp0SPLcZIIgCJJHJSIiIiIiIiIivdauXTv4+Phg5cqVAACVSgUnJyeMGTMGU6dOLdb+7bffhkKhwL59+8Rjr7/+Otq0aYPo6Ogqy1vXylu3ogoKClCjRg2sXLkSgwYNqux09YY2dSsoKEDHjh0xZMgQnDhxAqmpqWX6hvirpLx1i46OxqJFi3DlyhUYGxtXdbp6pby1Gz16NJKSknD06FHx2AcffIBffvkFJ0+erLK89YVMJsPOnTtfOBMqMjIS+/fv1xjQ7t+/P1JTU3Hw4EFJ8+GMDCIiIiIiIiKiaiYvLw/nzp1DYGCgeMzAwACBgYE4depUieecOnVKoz0ABAUFldr+VaRN3YrKysqCUqmEnZ1dZaWpd7St29y5c2Fvb4+IiIiqSFPvaFO3PXv2wNfXF++//z7q1KmDFi1aYMGCBSgoKKiqtPWCNrVr3749zp07Jy4/devWLcTFxaFHjx5VkvM/UVX+XTCSPCIREREREREREem1x48fo6CgAHXq1NE4XqdOHVy5cqXEcx48eFBi+wcPHlRanvpGm7oVFRkZibp16xa7+fcq06ZuJ0+exLp165CYmFgFGeonbep269YtHDt2DKGhoYiLi8ONGzcwatQoKJVKREVFVUXaekGb2r377rt4/Pgx/vWvf0EQBOTn52PkyJHVammp8irt70J6ejqys7NhZmYm2bU4I4OIiIiIiIiIiKgKfPzxx9i8eTN27twJU1NTXaejtzIyMjBw4ECsWbMGtWrV0nU6/ygqlQr29vb46quv4OXlhbfffhsffvhhtVr+TVvx8fFYsGABvvjiC5w/fx47duzA/v37MW/ePF2nRuCMDCIiIiIiIiKiaqdWrVowNDTEw4cPNY4/fPgQDg4OJZ7j4OBQrvavIm3qprZ48WJ8/PHHOHLkCFq1alWZaeqd8tbt5s2bSElJQXBwsHhMpVIBAIyMjHD16lW4uLhUbtJ6QJv3m6OjI4yNjWFoaCgec3d3x4MHD5CXlwcTE5NKzVlfaFO7mTNnYuDAgRg6dCgAoGXLllAoFBg+fDg+/PBDGBhwTkBRpf1dsLa2lnQ2BsAZGURERERERERE1Y6JiQm8vLw0NrVVqVQ4evQofH19SzzH19dXoz0AHD58uNT2ryJt6gYAn376KebNm4eDBw/C29u7KlLVK+WtW9OmTXHp0iUkJiaKP71790ZAQAASExPh5ORUlenrjDbvNz8/P9y4cUMc+AGAa9euwdHRsdoMYgDa1S4rK6vYYIV6QEgQhMpL9h+sKv8ucEYGEREREREREVE1NHHiRISFhcHb2xtt27bF8uXLoVAoEB4eDgAYNGgQ6tWrh4ULFwIAxo0bh06dOmHJkiXo2bMnNm/ejLNnz+Krr77SZTeqXHnr9sknn2DWrFnYtGkTGjZsKO4pYmlpCUtLS531o6qVp26mpqZo0aKFxvm2trYAUOz4q66877f33nsPK1euxLhx4zBmzBhcv34dCxYswNixY3XZDZ0ob+2Cg4OxdOlSeHh4oF27drhx4wZmzpyJ4OBgjRkur7LMzEzcuHFDfJycnIzExETY2dnB2dkZ06ZNw71797B+/XoAwMiRI7Fy5UpMmTIFQ4YMwbFjx7B161bs379f8tw4kEFEREREREREVA29/fbb+OuvvzBr1iw8ePAAbdq0wcGDB8WNW+/cuaPx7eT27dtj06ZNmDFjBqZPn47XXnsNu3btqnY3lstbt9WrVyMvLw9vvfWWRpyoqCjMnj27KlPXqfLWjZ4rb92cnJxw6NAhTJgwAa1atUK9evUwbtw4REZG6qoLOlPe2s2YMQMymQwzZszAvXv3ULt2bQQHB2P+/Pm66kKVO3v2LAICAsTHEydOBACEhYUhNjYW9+/fx507d8TnGzVqhP3792PChAlYsWIF6tevj7Vr1yIoKEjy3GQC58UQEREREREREREREZGe4jAnERERERERERERERHpLQ5kEBERERERERERERGR3uJABhERERERERERERER6S0OZBARERERERERERERkd7iQAYREREREREREREREektDmQQEREREREREREREZHe4kAGERERERERERERERHpLQ5kEBERERERERERERGR3uJABhEREREREREREZEeO3jwINq0aQNTU1PIZDKkpqbqOiWiKsWBDCIiIiIiIiIiomoiNjYWMplM/DE1NYWrqytGjx6Nhw8f6jq9Cvv9998xe/ZspKSk6DoVyTx58gT9+vWDmZkZVq1ahQ0bNsDCwqLEtiW9vnXr1kVQUBA+++wzZGRkaJ3HTz/9hNmzZ3MQhXTCSNcJEBERERERERERUdWaO3cuGjVqhJycHJw8eRKrV69GXFwcLl++DHNzc12np7Xff/8dc+bMgb+/Pxo2bKjrdCRx5swZZGRkYN68eQgMDCzTOerXV6lU4sGDB4iPj8f48eOxdOlS7NmzB61atSp3Hj/99BPmzJmDwYMHw9bWttznE1UEBzKIiIiIiIiIiIiqmTfeeAPe3t4AgKFDh6JmzZpYunQpdu/ejXfeeadCsbOysv7RgyH65tGjRwBQrsGDwq8vAEybNg3Hjh1Dr1690Lt3byQlJcHMzEzqVIkqDZeWIiIiIiIiIiIiquY6d+4MAEhOThaPffvtt/Dy8oKZmRns7OzQv39/3L17V+M8f39/tGjRAufOnUPHjh1hbm6O6dOnAwBycnIwe/ZsuLq6wtTUFI6OjujTpw9u3rwpnq9SqbB8+XI0b94cpqamqFOnDkaMGIFnz55pXKdhw4bo1asXTp48ibZt28LU1BSNGzfG+vXrxTaxsbHo27cvACAgIEBcXik+Ph4AsHv3bvTs2RN169aFXC6Hi4sL5s2bh4KCgmL1WLVqFRo3bgwzMzO0bdsWJ06cgL+/P/z9/TXa5ebmIioqCk2aNIFcLoeTkxOmTJmC3NzcMtV927ZtYo1r1aqFAQMG4N69exr1DQsLAwD4+PhAJpNh8ODBZYpdVOfOnTFz5kzcvn0b3377rXj8119/xeDBg9G4cWOYmprCwcEBQ4YMwZMnT8Q2s2fPxuTJkwEAjRo1EmurXsIrJiYGnTt3hr29PeRyOZo1a4bVq1drlSdRSTgjg4iIiIiIiIiIqJpTDy7UrFkTADB//nzMnDkT/fr1w9ChQ/HXX3/h888/R8eOHXHhwgWN2QFPnjzBG2+8gf79+2PAgAGoU6cOCgoK0KtXLxw9ehT9+/fHuHHjkJGRgcOHD+Py5ctwcXEBAIwYMQKxsbEIDw/H2LFjkZycjJUrV+LChQtISEiAsbGxeJ0bN27grbfeQkREBMLCwvD1119j8ODB8PLyQvPmzdGxY0eMHTsWn332GaZPnw53d3cAEP8bGxsLS0tLTJw4EZaWljh27BhmzZqF9PR0LFq0SLzO6tWrMXr0aHTo0AETJkxASkoKQkJCUKNGDdSvX19sp1Kp0Lt3b5w8eRLDhw+Hu7s7Ll26hGXLluHatWvYtWvXC2uu7rePjw8WLlyIhw8fYsWKFUhISBBr/OGHH8LNzQ1fffWVuFyUunbaGDhwIKZPn47vv/8ew4YNAwAcPnwYt27dQnh4OBwcHPDbb7/hq6++wm+//Yaff/4ZMpkMffr0wbVr1/Ddd99h2bJlqFWrFgCgdu3aYs2aN2+O3r17w8jICHv37sWoUaOgUqnw/vvva50vkUggIiIiIiIiIiKiaiEmJkYAIBw5ckT466+/hLt37wqbN28WatasKZiZmQl//PGHkJKSIhgaGgrz58/XOPfSpUuCkZGRxvFOnToJAITo6GiNtl9//bUAQFi6dGmxHFQqlSAIgnDixAkBgLBx40aN5w8ePFjseIMGDQQAwo8//igee/TokSCXy4UPPvhAPLZt2zYBgHD8+PFi183Kyip2bMSIEYK5ubmQk5MjCIIg5ObmCjVr1hR8fHwEpVIptouNjRUACJ06dRKPbdiwQTAwMBBOnDihETM6OloAICQkJBS7nlpeXp5gb28vtGjRQsjOzhaP79u3TwAgzJo1Szymfs3OnDlTarzytLWxsRE8PDzExyXV5bvvvitW70WLFgkAhOTk5GLtS4oRFBQkNG7c+KU5E5UFl5YiIiIiIiIiIiKqZgIDA1G7dm04OTmhf//+sLS0xM6dO1GvXj3s2LEDKpUK/fr1w+PHj8UfBwcHvPbaazh+/LhGLLlcjvDwcI1j27dvR61atTBmzJhi15bJZACeL6tkY2ODrl27alzHy8sLlpaWxa7TrFkzdOjQQXxcu3ZtuLm54datW2Xqc+E9ITIyMvD48WN06NABWVlZuHLlCgDg7NmzePLkCYYNGwYjo78XswkNDUWNGjU04m3btg3u7u5o2rSpRv7qZbqK5l/Y2bNn8ejRI4waNQqmpqbi8Z49e6Jp06bYv39/mfqkDUtLS2RkZIiPC9clJycHjx8/xuuvvw4AOH/+fJliFo6RlpaGx48fo1OnTrh16xbS0tIkypyqMy4tRUREREREREREVM2sWrUKrq6uMDIyQp06deDm5gYDg+ffeb5+/ToEQcBrr71W4rmFl3sCgHr16sHExETj2M2bN+Hm5qYxGFDU9evXkZaWBnt7+xKfV29yrebs7FysTY0aNYrtp1Ga3377DTNmzMCxY8eQnp6u8Zz6Zvvt27cBAE2aNNF43sjICA0bNiyWf1JSkri80svyL0x9HTc3t2LPNW3aFCdPnnxxZyogMzNTo+ZPnz7FnDlzsHnz5mI5l3UQIiEhAVFRUTh16hSysrKKxbCxsal44lStcSCDiIiIiIiIiIiommnbti28vb1LfE6lUkEmk+HAgQMwNDQs9rylpaXG48Lfxi8PlUoFe3t7bNy4scTniw4QlJQLAAiC8NJrpaamolOnTrC2tsbcuXPh4uICU1NTnD9/HpGRkVCpVFrl37JlSyxdurTE552cnMods7L98ccfSEtL0xio6devH3766SdMnjwZbdq0gaWlJVQqFbp3716muty8eRNdunRB06ZNsXTpUjg5OcHExARxcXFYtmyZVrUlKooDGURERERERERERCRycXGBIAho1KgRXF1dtY7xyy+/QKlUFpvBUbjNkSNH4Ofnp/VgSFHqZauKio+Px5MnT7Bjxw507NhRPJ6cnKzRrkGDBgCebyweEBAgHs/Pz0dKSgpatWqlkf/FixfRpUuXUq9bGvV1rl69Ki5FpXb16lXxealt2LABABAUFAQAePbsGY4ePYo5c+Zg1qxZYrvr168XO7e0Pu7duxe5ubnYs2ePxqyZFy2tRVRe3CODiIiIiIiIiIiIRH369IGhoSHmzJlTbLaDIAh48uTJS2P85z//wePHj7Fy5cpiz6lj9uvXDwUFBZg3b16xNvn5+UhNTS137hYWFgBQ7Fz1bI7C/cnLy8MXX3yh0c7b2xs1a9bEmjVrkJ+fLx7fuHFjsSWs+vXrh3v37mHNmjXF8sjOzoZCoSg1T29vb9jb2yM6Ohq5ubni8QMHDiApKQk9e/Z8SU/L79ixY5g3bx4aNWqE0NBQACXXBQCWL19e7Pzy1DYtLQ0xMTFSpU7EGRlERERERERERET0NxcXF3z00UeYNm0aUlJSEBISAisrKyQnJ2Pnzp0YPnw4Jk2a9MIYgwYNwvr16zFx4kScPn0aHTp0gEKhwJEjRzBq1Ci8+eab6NSpE0aMGIGFCxciMTER3bp1g7GxMa5fv45t27ZhxYoVeOutt8qVe5s2bWBoaIhPPvkEaWlpkMvl6Ny5M9q3b48aNWogLCwMY8eOhUwmw4YNG4rdwDcxMcHs2bMxZswYdO7cGf369UNKSgpiY2Ph4uKiMSth4MCB2Lp1K0aOHInjx4/Dz88PBQUFuHLlCrZu3YpDhw6VunyXsbExPvnkE4SHh6NTp05455138PDhQ6xYsQINGzbEhAkTytXvog4cOIArV64gPz8fDx8+xLFjx3D48GE0aNAAe/bsETcYt7a2RseOHfHpp59CqVSiXr16+P7774vNVAEALy8vAMCHH36I/v37w9jYGMHBwejWrRtMTEwQHByMESNGIDMzE2vWrIG9vT3u379foX4QqXEgg4iIiIiIiIiIiDRMnToVrq6uWLZsGebMmQPg+Z4P3bp1Q+/evV96vqGhIeLi4jB//nxs2rQJ27dvR82aNfGvf/0LLVu2FNtFR0fDy8sLX375JaZPny5uqj1gwAD4+fmVO28HBwdER0dj4cKFiIiIQEFBAY4fPw5/f3/s27cPH3zwAWbMmIEaNWpgwIAB6NKli7jMktro0aMhCAKWLFmCSZMmoXXr1tizZw/Gjh0rDgAAgIGBAXbt2oVly5Zh/fr12LlzJ8zNzdG4cWOMGzfupctyDR48GObm5vj4448RGRkJCwsL/Pvf/8Ynn3wCW1vbcve9MPUyUSYmJrCzs0PLli2xfPlyhIeHw8rKSqPtpk2bMGbMGKxatQqCIKBbt244cOAA6tatq9HOx8cH8+bNQ3R0NA4ePAiVSoXk5GS4ubnhv//9L2bMmIFJkybBwcEB7733HmrXro0hQ4ZUqB9EajKhLLvhEBEREREREREREVVTKpUKtWvXRp8+fUpcSoqIKhf3yCAiIiIiIiIiIiL6v5ycnGJLTq1fvx5Pnz6Fv7+/bpIiquY4I4OIiIiIiIiIiIjo/+Lj4zFhwgT07dsXNWvWxPnz57Fu3Tq4u7vj3LlzMDEx0XWKRNUO98ggIiIiIiIiIiIi+r+GDRvCyckJn332GZ4+fQo7OzsMGjQIH3/8MQcxiHSEMzKIiIiIiIiIiIiIiEhvcY8MIiIiIiIiIiIiIiLSWxzIICIiIiIiIiIiIiIivcWBDCIiIiIiIiIiIiIi0lscyCAiIiIiIiIiIiIiIr3FgQwiIiIiIiIiIiIiItJbHMggIiIiIiIiIiIiIiK9xYEMIiIiIiIiIiIiIiLSWxzIICIiIiIiIiIiIiIivcWBDCIiIiIiIiIiIiIi0lv/AyqpqFPAd+OFAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 1600x700 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import RocCurveDisplay, PrecisionRecallDisplay\n",
    "from sklearn.metrics import precision_recall_curve\n",
    "\n",
    "# Helper function to compute cumulative gain and lift\n",
    "# Helper function to compute cumulative gain and lift\n",
    "def compute_lift(y_true, y_prob):\n",
    "    # Sort the predictions by the probabilities in descending order\n",
    "    sorted_indices = np.argsort(-y_prob)\n",
    "\n",
    "    # Get the values of y_true as a NumPy array to allow positional indexing\n",
    "    y_true_values = y_true.values\n",
    "    y_true_sorted = y_true_values[sorted_indices]\n",
    "\n",
    "    # Cumulative sum of positive instances\n",
    "    cumulative_positive = np.cumsum(y_true_sorted)\n",
    "    total_positives = np.sum(y_true_values) # Use y_true_values here too\n",
    "\n",
    "    # Cumulative gain is the ratio of cumulative positives to total positives\n",
    "    cumulative_gain = cumulative_positive / total_positives\n",
    "\n",
    "    # Lift is the cumulative gain divided by the baseline (which is the cumulative percentage of data)\n",
    "    percentage_data = np.arange(1, len(y_true_sorted) + 1) / len(y_true_sorted)\n",
    "    lift = cumulative_gain / percentage_data\n",
    "\n",
    "    return percentage_data, lift\n",
    "\n",
    "# Compute lift for the current and previous models\n",
    "percentage_data_2, lift_2 = compute_lift(y_test_norm, logreg_2.predict_proba(X_test_norm)[:, 1])\n",
    "percentage_data_1, lift_1 = compute_lift(y_test_prev, logreg_1.predict_proba(X_test_prev)[:, 1])\n",
    "\n",
    "plt.figure(figsize=(16, 7))\n",
    "\n",
    "# ROC curve with green for the current model and red for the previous model\n",
    "plt.subplot(1, 3, 1)\n",
    "ax1 = plt.gca()\n",
    "RocCurveDisplay.from_estimator(logreg_2, X_test_norm, y_test_norm, ax=ax1, color='green', name='Log-Reg-VIF-Influence-Removed-Model')\n",
    "RocCurveDisplay.from_estimator(logreg_1, X_test_prev, y_test_prev, ax=ax1, color='red', name='Log-Reg-Base-Model')\n",
    "\n",
    "# Adding diagonal line for a random classifier\n",
    "ax1.plot([0, 1], [0, 1], 'k--', lw=2, label='Random Classifier')\n",
    "\n",
    "ax1.set_title('ROC Curve (Test Set)', fontsize=14)\n",
    "ax1.grid(True, which='both', linestyle='--', linewidth=0.5)\n",
    "ax1.minorticks_on()\n",
    "ax1.legend(loc='lower right')\n",
    "\n",
    "# Precision-Recall curve with green for the current model and red for the previous model\n",
    "plt.subplot(1, 3, 2)\n",
    "ax2 = plt.gca()\n",
    "PrecisionRecallDisplay.from_estimator(logreg_2, X_test_norm, y_test_norm, ax=ax2, color='green', name='Log-Reg-VIF-Influence-Removed-Model')\n",
    "PrecisionRecallDisplay.from_estimator(logreg_1, X_test_prev, y_test_prev, ax=ax2, color='red', name='Log-Reg-Base-Model')\n",
    "\n",
    "ax2.set_title('Precision-Recall Curve (Test Set)', fontsize=14)\n",
    "ax2.grid(True, which='both', linestyle='--', linewidth=0.5)\n",
    "ax2.minorticks_on()\n",
    "\n",
    "# Lift curve\n",
    "plt.subplot(1, 3, 3)\n",
    "plt.plot(percentage_data_2, lift_2, label='Log-Reg-VIF-Influence-Removed-Model', color='green')\n",
    "plt.plot(percentage_data_1, lift_1, label='Log-Reg-Base-Model', color='red')\n",
    "\n",
    "plt.title('Lift Curve (Test Set)', fontsize=14)\n",
    "plt.xlabel('Percentage of Data', fontsize=12)\n",
    "plt.ylabel('Lift', fontsize=12)\n",
    "\n",
    "# Enable both major and minor ticks\n",
    "plt.minorticks_on()\n",
    "\n",
    "# Major and minor gridlines\n",
    "plt.grid(True, which='major', linestyle='-', linewidth=0.7)  # Major gridlines\n",
    "plt.grid(True, which='minor', linestyle='--', linewidth=0.3)  # Minor gridlines\n",
    "\n",
    "plt.legend(loc='best')\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 231
    },
    "id": "5qj4Neh_ymt5",
    "outputId": "34a2546d-7acb-4735-b4f6-ed8e61d1fad2"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "scores"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-a47347fa-1611-45f7-922f-b9f5a78f9322\" 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>Model</th>\n",
       "      <th>Accuracy_Train</th>\n",
       "      <th>Precision_Train</th>\n",
       "      <th>Recall_Train</th>\n",
       "      <th>F1_Train</th>\n",
       "      <th>ROC_AUC_Train</th>\n",
       "      <th>Cohen_Kappa_Train</th>\n",
       "      <th>Accuracy_Test</th>\n",
       "      <th>Precision_Test</th>\n",
       "      <th>Recall_Test</th>\n",
       "      <th>...</th>\n",
       "      <th>ROC_AUC_Test</th>\n",
       "      <th>Cohen_Kappa_Test</th>\n",
       "      <th>Weighted_Precision_Train</th>\n",
       "      <th>Weighted_Recall_Train</th>\n",
       "      <th>Macro_Precision_Train</th>\n",
       "      <th>Macro_Recall_Train</th>\n",
       "      <th>Weighted_Precision_Test</th>\n",
       "      <th>Weighted_Recall_Test</th>\n",
       "      <th>Macro_Precision_Test</th>\n",
       "      <th>Macro_Recall_Test</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Logistic Regression</td>\n",
       "      <td>0.560625</td>\n",
       "      <td>0.559905</td>\n",
       "      <td>0.587065</td>\n",
       "      <td>0.573163</td>\n",
       "      <td>0.587135</td>\n",
       "      <td>0.121014</td>\n",
       "      <td>0.56</td>\n",
       "      <td>0.56068</td>\n",
       "      <td>0.574627</td>\n",
       "      <td>...</td>\n",
       "      <td>0.576146</td>\n",
       "      <td>0.119868</td>\n",
       "      <td>0.560662</td>\n",
       "      <td>0.560625</td>\n",
       "      <td>0.560666</td>\n",
       "      <td>0.560492</td>\n",
       "      <td>0.559982</td>\n",
       "      <td>0.56</td>\n",
       "      <td>0.559979</td>\n",
       "      <td>0.559926</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Logistic-Regr + VIF + Infl.removal</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 21 columns</p>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a47347fa-1611-45f7-922f-b9f5a78f9322')\"\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-a47347fa-1611-45f7-922f-b9f5a78f9322 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-a47347fa-1611-45f7-922f-b9f5a78f9322');\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-4502c322-f578-4411-a3ca-09ea336459a5\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-4502c322-f578-4411-a3ca-09ea336459a5')\"\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-4502c322-f578-4411-a3ca-09ea336459a5 button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "\n",
       "  <div id=\"id_f47fa33a-c2cc-44aa-8d1a-56098450340d\">\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('scores')\"\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_f47fa33a-c2cc-44aa-8d1a-56098450340d button.colab-df-generate');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      buttonEl.onclick = () => {\n",
       "        google.colab.notebook.generateWithVariable('scores');\n",
       "      }\n",
       "      })();\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "                                Model  Accuracy_Train  Precision_Train  \\\n",
       "0                 Logistic Regression        0.560625         0.559905   \n",
       "1  Logistic-Regr + VIF + Infl.removal        1.000000         1.000000   \n",
       "\n",
       "   Recall_Train  F1_Train  ROC_AUC_Train  Cohen_Kappa_Train  Accuracy_Test  \\\n",
       "0      0.587065  0.573163       0.587135           0.121014           0.56   \n",
       "1      1.000000  1.000000       1.000000           1.000000           1.00   \n",
       "\n",
       "   Precision_Test  Recall_Test  ...  ROC_AUC_Test  Cohen_Kappa_Test  \\\n",
       "0         0.56068     0.574627  ...      0.576146          0.119868   \n",
       "1         1.00000     1.000000  ...      1.000000          1.000000   \n",
       "\n",
       "   Weighted_Precision_Train  Weighted_Recall_Train  Macro_Precision_Train  \\\n",
       "0                  0.560662               0.560625               0.560666   \n",
       "1                  1.000000               1.000000               1.000000   \n",
       "\n",
       "   Macro_Recall_Train  Weighted_Precision_Test  Weighted_Recall_Test  \\\n",
       "0            0.560492                 0.559982                  0.56   \n",
       "1            1.000000                 1.000000                  1.00   \n",
       "\n",
       "   Macro_Precision_Test  Macro_Recall_Test  \n",
       "0              0.559979           0.559926  \n",
       "1              1.000000           1.000000  \n",
       "\n",
       "[2 rows x 21 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Call the classification metrics function\n",
    "scores = get_classification_metrics(\n",
    "    y_train=y_train_norm,\n",
    "    y_train_pred=y_train_pred2,\n",
    "    y_train_prob=y_train_prob,\n",
    "    y_test=y_test_norm,\n",
    "    y_test_pred=y_test_pred2,\n",
    "    y_test_prob=y_test_prob,\n",
    "    model_name=\"Logistic-Regr + VIF + Infl.removal\",\n",
    "    scores=scores\n",
    ")\n",
    "\n",
    "# Display the updated scores DataFrame\n",
    "scores"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Ds4JicKB3u4O"
   },
   "source": [
    "![image.png](data:image/png;base64,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)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "JP7a5tVhfa40"
   },
   "source": [
    "#### `In-Class Activity - 2:` Duration: 15 minutes\n",
    " Train a logistic regression model and interpret the predicted probabilities for a small set of instances. Learners will reflect on the confidence of the model and how it assigns probabilities to different classes.\n",
    "\n",
    "`Steps for the Activity:`\n",
    "\n",
    "`Train the Model:`\n",
    "- Train a logistic regression model using the provided dataset.\n",
    "\n",
    "`Predict Probabilities:`\n",
    "- Use the model to predict the class probabilities for a small subset of test data (e.g., 5 instances).\n",
    "\n",
    "`Interpret the Probabilities:`\n",
    "- Print the predicted probabilities to interpret what they mean. For instance, discuss how confident the model is about its prediction and which class is most likely."
   ]
  }
 ],
 "metadata": {
  "accelerator": "TPU",
  "colab": {
   "gpuType": "V28",
   "machine_shape": "hm",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}