Stock_Price_Prediction.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMPdLYBDsaQUOmzEd98klA0",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Premrufus/BharatIntenRepo/blob/main/Stock_Price_Prediction.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **DATA SCIENCE INTERN - BHARAT INTERN**"
      ],
      "metadata": {
        "id": "eQO-AqPeEWci"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **TASK 1 - Stock Prediction**"
      ],
      "metadata": {
        "id": "HV9wJtbkEj36"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Problem Statement:** To predict Stock Price of a Company using LSTM"
      ],
      "metadata": {
        "id": "UhAxeGOuDgDB"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "#### **About Dataset**\n",
        "\n",
        "The Google stock dataset contains historical data of Google's stock prices and related attributes. It consists of 14 columns and 1257 rows. Each column represents a specific attribute, and each row contains the corresponding values for that attribute.\n",
        "\n",
        "The columns in the dataset are as follows:\n",
        "\n",
        "* Symbol: The name of the company, which is GOOG in this case.\n",
        "* Date: The year and date of the stock data.\n",
        "* Close: The closing price of Google's stock on a particular day.\n",
        "* High: The highest value reached by Google's stock on the given day.\n",
        "* Low: The lowest value reached by Google's stock on the given day.\n",
        "* Open: The opening value of Google's stock on the given day.\n",
        "* Volume: The trading volume of Google's stock on the given day, i.e., the number of shares traded.\n",
        "* adjClose: The adjusted closing price of Google's stock, considering factors such as dividends and stock splits.\n",
        "* adjHigh: The adjusted highest value reached by Google's stock on the given day.\n",
        "* adjLow: The adjusted lowest value reached by Google's stock on the given day.\n",
        "* adjOpen: The adjusted opening value of Google's stock on the given day.\n",
        "* adjVolume: The adjusted trading volume of Google's stock on the given day, accounting for factors such as stock splits.\n",
        "* divCash: The amount of cash dividend paid out to shareholders on the given day.\n",
        "* splitFactor: The split factor, if any, applied to Google's stock on the given day. A split factor of 1 indicates no split.\n",
        "\n",
        "This dataset can be used for a variety of purposes, such as:\n",
        "\n",
        "* Analyzing the historical performance of Google's stock.\n",
        "* Building predictive models to forecast Google's future stock prices.\n",
        "* Developing trading strategies to profit from the movement of Google's stock prices.\n",
        "\n",
        "The dataset is available in CSV format and can be downloaded from [Kaggle](https://www.kaggle.com/datasets/shreenidhihipparagi/google-stock-prediction/)."
      ],
      "metadata": {
        "id": "N4vcNAoiIFDC"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Importing Libraries and Dataset to be used**"
      ],
      "metadata": {
        "id": "36oC-zK3En2H"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#importing libraries to be used\n",
        "import numpy as np # for linear algebra\n",
        "import pandas as pd # data preprocessing\n",
        "import matplotlib.pyplot as plt # data visualization library\n",
        "import seaborn as sns # data visualization library\n",
        "%matplotlib inline\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore') # ignore warnings\n",
        "\n",
        "from sklearn.preprocessing import MinMaxScaler # for normalization\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Dropout, LSTM, Bidirectional"
      ],
      "metadata": {
        "id": "7eA6ZoD_DdgY"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv('Google Stocks.csv') # data_importing\n",
        "df.head(10) # fetching first 10 rows of dataset"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "TKB8x1wqDdsj",
        "outputId": "d3783c90-d21e-4920-c1a7-113a8a0f6cd0"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  symbol                       date   close    high       low    open  \\\n",
              "0   GOOG  2016-06-14 00:00:00+00:00  718.27  722.47  713.1200  716.48   \n",
              "1   GOOG  2016-06-15 00:00:00+00:00  718.92  722.98  717.3100  719.00   \n",
              "2   GOOG  2016-06-16 00:00:00+00:00  710.36  716.65  703.2600  714.91   \n",
              "3   GOOG  2016-06-17 00:00:00+00:00  691.72  708.82  688.4515  708.65   \n",
              "4   GOOG  2016-06-20 00:00:00+00:00  693.71  702.48  693.4100  698.77   \n",
              "5   GOOG  2016-06-21 00:00:00+00:00  695.94  702.77  692.0100  698.40   \n",
              "6   GOOG  2016-06-22 00:00:00+00:00  697.46  700.86  693.0819  699.06   \n",
              "7   GOOG  2016-06-23 00:00:00+00:00  701.87  701.95  687.0000  697.45   \n",
              "8   GOOG  2016-06-24 00:00:00+00:00  675.22  689.40  673.4500  675.17   \n",
              "9   GOOG  2016-06-27 00:00:00+00:00  668.26  672.30  663.2840  671.00   \n",
              "\n",
              "    volume  adjClose  adjHigh    adjLow  adjOpen  adjVolume  divCash  \\\n",
              "0  1306065    718.27   722.47  713.1200   716.48    1306065      0.0   \n",
              "1  1214517    718.92   722.98  717.3100   719.00    1214517      0.0   \n",
              "2  1982471    710.36   716.65  703.2600   714.91    1982471      0.0   \n",
              "3  3402357    691.72   708.82  688.4515   708.65    3402357      0.0   \n",
              "4  2082538    693.71   702.48  693.4100   698.77    2082538      0.0   \n",
              "5  1465634    695.94   702.77  692.0100   698.40    1465634      0.0   \n",
              "6  1184318    697.46   700.86  693.0819   699.06    1184318      0.0   \n",
              "7  2171415    701.87   701.95  687.0000   697.45    2171415      0.0   \n",
              "8  4449022    675.22   689.40  673.4500   675.17    4449022      0.0   \n",
              "9  2641085    668.26   672.30  663.2840   671.00    2641085      0.0   \n",
              "\n",
              "   splitFactor  \n",
              "0          1.0  \n",
              "1          1.0  \n",
              "2          1.0  \n",
              "3          1.0  \n",
              "4          1.0  \n",
              "5          1.0  \n",
              "6          1.0  \n",
              "7          1.0  \n",
              "8          1.0  \n",
              "9          1.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a27c2eae-3117-4bcf-9360-125cbdc1716d\" 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>symbol</th>\n",
              "      <th>date</th>\n",
              "      <th>close</th>\n",
              "      <th>high</th>\n",
              "      <th>low</th>\n",
              "      <th>open</th>\n",
              "      <th>volume</th>\n",
              "      <th>adjClose</th>\n",
              "      <th>adjHigh</th>\n",
              "      <th>adjLow</th>\n",
              "      <th>adjOpen</th>\n",
              "      <th>adjVolume</th>\n",
              "      <th>divCash</th>\n",
              "      <th>splitFactor</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-14 00:00:00+00:00</td>\n",
              "      <td>718.27</td>\n",
              "      <td>722.47</td>\n",
              "      <td>713.1200</td>\n",
              "      <td>716.48</td>\n",
              "      <td>1306065</td>\n",
              "      <td>718.27</td>\n",
              "      <td>722.47</td>\n",
              "      <td>713.1200</td>\n",
              "      <td>716.48</td>\n",
              "      <td>1306065</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-15 00:00:00+00:00</td>\n",
              "      <td>718.92</td>\n",
              "      <td>722.98</td>\n",
              "      <td>717.3100</td>\n",
              "      <td>719.00</td>\n",
              "      <td>1214517</td>\n",
              "      <td>718.92</td>\n",
              "      <td>722.98</td>\n",
              "      <td>717.3100</td>\n",
              "      <td>719.00</td>\n",
              "      <td>1214517</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-16 00:00:00+00:00</td>\n",
              "      <td>710.36</td>\n",
              "      <td>716.65</td>\n",
              "      <td>703.2600</td>\n",
              "      <td>714.91</td>\n",
              "      <td>1982471</td>\n",
              "      <td>710.36</td>\n",
              "      <td>716.65</td>\n",
              "      <td>703.2600</td>\n",
              "      <td>714.91</td>\n",
              "      <td>1982471</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-17 00:00:00+00:00</td>\n",
              "      <td>691.72</td>\n",
              "      <td>708.82</td>\n",
              "      <td>688.4515</td>\n",
              "      <td>708.65</td>\n",
              "      <td>3402357</td>\n",
              "      <td>691.72</td>\n",
              "      <td>708.82</td>\n",
              "      <td>688.4515</td>\n",
              "      <td>708.65</td>\n",
              "      <td>3402357</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-20 00:00:00+00:00</td>\n",
              "      <td>693.71</td>\n",
              "      <td>702.48</td>\n",
              "      <td>693.4100</td>\n",
              "      <td>698.77</td>\n",
              "      <td>2082538</td>\n",
              "      <td>693.71</td>\n",
              "      <td>702.48</td>\n",
              "      <td>693.4100</td>\n",
              "      <td>698.77</td>\n",
              "      <td>2082538</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-21 00:00:00+00:00</td>\n",
              "      <td>695.94</td>\n",
              "      <td>702.77</td>\n",
              "      <td>692.0100</td>\n",
              "      <td>698.40</td>\n",
              "      <td>1465634</td>\n",
              "      <td>695.94</td>\n",
              "      <td>702.77</td>\n",
              "      <td>692.0100</td>\n",
              "      <td>698.40</td>\n",
              "      <td>1465634</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-22 00:00:00+00:00</td>\n",
              "      <td>697.46</td>\n",
              "      <td>700.86</td>\n",
              "      <td>693.0819</td>\n",
              "      <td>699.06</td>\n",
              "      <td>1184318</td>\n",
              "      <td>697.46</td>\n",
              "      <td>700.86</td>\n",
              "      <td>693.0819</td>\n",
              "      <td>699.06</td>\n",
              "      <td>1184318</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-23 00:00:00+00:00</td>\n",
              "      <td>701.87</td>\n",
              "      <td>701.95</td>\n",
              "      <td>687.0000</td>\n",
              "      <td>697.45</td>\n",
              "      <td>2171415</td>\n",
              "      <td>701.87</td>\n",
              "      <td>701.95</td>\n",
              "      <td>687.0000</td>\n",
              "      <td>697.45</td>\n",
              "      <td>2171415</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-24 00:00:00+00:00</td>\n",
              "      <td>675.22</td>\n",
              "      <td>689.40</td>\n",
              "      <td>673.4500</td>\n",
              "      <td>675.17</td>\n",
              "      <td>4449022</td>\n",
              "      <td>675.22</td>\n",
              "      <td>689.40</td>\n",
              "      <td>673.4500</td>\n",
              "      <td>675.17</td>\n",
              "      <td>4449022</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>GOOG</td>\n",
              "      <td>2016-06-27 00:00:00+00:00</td>\n",
              "      <td>668.26</td>\n",
              "      <td>672.30</td>\n",
              "      <td>663.2840</td>\n",
              "      <td>671.00</td>\n",
              "      <td>2641085</td>\n",
              "      <td>668.26</td>\n",
              "      <td>672.30</td>\n",
              "      <td>663.2840</td>\n",
              "      <td>671.00</td>\n",
              "      <td>2641085</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</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-a27c2eae-3117-4bcf-9360-125cbdc1716d')\"\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-a27c2eae-3117-4bcf-9360-125cbdc1716d 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-a27c2eae-3117-4bcf-9360-125cbdc1716d');\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-671d3f45-600e-4d2c-824c-32361595127d\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-671d3f45-600e-4d2c-824c-32361595127d')\"\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-671d3f45-600e-4d2c-824c-32361595127d button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Gathering Insights**"
      ],
      "metadata": {
        "id": "AqvqUH1WEttg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "print(\"Shape of data:\",df.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Uq1QpjvDExGI",
        "outputId": "bca7e6ad-c9ca-48c9-ad07-a937c3977e7a"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Shape of data: (1258, 14)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# statistical description of data\n",
        "df.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 320
        },
        "id": "8ch4qYIeFFXx",
        "outputId": "6f7cc8c4-f573-4d67-d266-530b6a3b6fc6"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             close         high          low         open        volume  \\\n",
              "count  1258.000000  1258.000000  1258.000000  1258.000000  1.258000e+03   \n",
              "mean   1216.317067  1227.430934  1204.176430  1215.260779  1.601590e+06   \n",
              "std     383.333358   387.570872   378.777094   382.446995  6.960172e+05   \n",
              "min     668.260000   672.300000   663.284000   671.000000  3.467530e+05   \n",
              "25%     960.802500   968.757500   952.182500   959.005000  1.173522e+06   \n",
              "50%    1132.460000  1143.935000  1117.915000  1131.150000  1.412588e+06   \n",
              "75%    1360.595000  1374.345000  1348.557500  1361.075000  1.812156e+06   \n",
              "max    2521.600000  2526.990000  2498.290000  2524.920000  6.207027e+06   \n",
              "\n",
              "          adjClose      adjHigh       adjLow      adjOpen     adjVolume  \\\n",
              "count  1258.000000  1258.000000  1258.000000  1258.000000  1.258000e+03   \n",
              "mean   1216.317067  1227.430936  1204.176436  1215.260779  1.601590e+06   \n",
              "std     383.333358   387.570873   378.777099   382.446995  6.960172e+05   \n",
              "min     668.260000   672.300000   663.284000   671.000000  3.467530e+05   \n",
              "25%     960.802500   968.757500   952.182500   959.005000  1.173522e+06   \n",
              "50%    1132.460000  1143.935000  1117.915000  1131.150000  1.412588e+06   \n",
              "75%    1360.595000  1374.345000  1348.557500  1361.075000  1.812156e+06   \n",
              "max    2521.600000  2526.990000  2498.290000  2524.920000  6.207027e+06   \n",
              "\n",
              "       divCash  splitFactor  \n",
              "count   1258.0       1258.0  \n",
              "mean       0.0          1.0  \n",
              "std        0.0          0.0  \n",
              "min        0.0          1.0  \n",
              "25%        0.0          1.0  \n",
              "50%        0.0          1.0  \n",
              "75%        0.0          1.0  \n",
              "max        0.0          1.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d66d598d-5812-4a3d-b22c-fef603ad2c58\" 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>close</th>\n",
              "      <th>high</th>\n",
              "      <th>low</th>\n",
              "      <th>open</th>\n",
              "      <th>volume</th>\n",
              "      <th>adjClose</th>\n",
              "      <th>adjHigh</th>\n",
              "      <th>adjLow</th>\n",
              "      <th>adjOpen</th>\n",
              "      <th>adjVolume</th>\n",
              "      <th>divCash</th>\n",
              "      <th>splitFactor</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1.258000e+03</td>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1258.000000</td>\n",
              "      <td>1.258000e+03</td>\n",
              "      <td>1258.0</td>\n",
              "      <td>1258.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>1216.317067</td>\n",
              "      <td>1227.430934</td>\n",
              "      <td>1204.176430</td>\n",
              "      <td>1215.260779</td>\n",
              "      <td>1.601590e+06</td>\n",
              "      <td>1216.317067</td>\n",
              "      <td>1227.430936</td>\n",
              "      <td>1204.176436</td>\n",
              "      <td>1215.260779</td>\n",
              "      <td>1.601590e+06</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>383.333358</td>\n",
              "      <td>387.570872</td>\n",
              "      <td>378.777094</td>\n",
              "      <td>382.446995</td>\n",
              "      <td>6.960172e+05</td>\n",
              "      <td>383.333358</td>\n",
              "      <td>387.570873</td>\n",
              "      <td>378.777099</td>\n",
              "      <td>382.446995</td>\n",
              "      <td>6.960172e+05</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>668.260000</td>\n",
              "      <td>672.300000</td>\n",
              "      <td>663.284000</td>\n",
              "      <td>671.000000</td>\n",
              "      <td>3.467530e+05</td>\n",
              "      <td>668.260000</td>\n",
              "      <td>672.300000</td>\n",
              "      <td>663.284000</td>\n",
              "      <td>671.000000</td>\n",
              "      <td>3.467530e+05</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>960.802500</td>\n",
              "      <td>968.757500</td>\n",
              "      <td>952.182500</td>\n",
              "      <td>959.005000</td>\n",
              "      <td>1.173522e+06</td>\n",
              "      <td>960.802500</td>\n",
              "      <td>968.757500</td>\n",
              "      <td>952.182500</td>\n",
              "      <td>959.005000</td>\n",
              "      <td>1.173522e+06</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>1132.460000</td>\n",
              "      <td>1143.935000</td>\n",
              "      <td>1117.915000</td>\n",
              "      <td>1131.150000</td>\n",
              "      <td>1.412588e+06</td>\n",
              "      <td>1132.460000</td>\n",
              "      <td>1143.935000</td>\n",
              "      <td>1117.915000</td>\n",
              "      <td>1131.150000</td>\n",
              "      <td>1.412588e+06</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>1360.595000</td>\n",
              "      <td>1374.345000</td>\n",
              "      <td>1348.557500</td>\n",
              "      <td>1361.075000</td>\n",
              "      <td>1.812156e+06</td>\n",
              "      <td>1360.595000</td>\n",
              "      <td>1374.345000</td>\n",
              "      <td>1348.557500</td>\n",
              "      <td>1361.075000</td>\n",
              "      <td>1.812156e+06</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>2521.600000</td>\n",
              "      <td>2526.990000</td>\n",
              "      <td>2498.290000</td>\n",
              "      <td>2524.920000</td>\n",
              "      <td>6.207027e+06</td>\n",
              "      <td>2521.600000</td>\n",
              "      <td>2526.990000</td>\n",
              "      <td>2498.290000</td>\n",
              "      <td>2524.920000</td>\n",
              "      <td>6.207027e+06</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</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-d66d598d-5812-4a3d-b22c-fef603ad2c58')\"\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-d66d598d-5812-4a3d-b22c-fef603ad2c58 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-d66d598d-5812-4a3d-b22c-fef603ad2c58');\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-7c6b5958-ab0b-4025-8ad1-9afa47cb9926\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-7c6b5958-ab0b-4025-8ad1-9afa47cb9926')\"\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-7c6b5958-ab0b-4025-8ad1-9afa47cb9926 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# summary of data\n",
        "df.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qf5pINMYFIVf",
        "outputId": "69cabf6a-a099-47ea-deb7-b45d85ba3128"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1258 entries, 0 to 1257\n",
            "Data columns (total 14 columns):\n",
            " #   Column       Non-Null Count  Dtype  \n",
            "---  ------       --------------  -----  \n",
            " 0   symbol       1258 non-null   object \n",
            " 1   date         1258 non-null   object \n",
            " 2   close        1258 non-null   float64\n",
            " 3   high         1258 non-null   float64\n",
            " 4   low          1258 non-null   float64\n",
            " 5   open         1258 non-null   float64\n",
            " 6   volume       1258 non-null   int64  \n",
            " 7   adjClose     1258 non-null   float64\n",
            " 8   adjHigh      1258 non-null   float64\n",
            " 9   adjLow       1258 non-null   float64\n",
            " 10  adjOpen      1258 non-null   float64\n",
            " 11  adjVolume    1258 non-null   int64  \n",
            " 12  divCash      1258 non-null   float64\n",
            " 13  splitFactor  1258 non-null   float64\n",
            "dtypes: float64(10), int64(2), object(2)\n",
            "memory usage: 137.7+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# checking null values\n",
        "df.isnull().sum()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "r-JY7rJvFKbh",
        "outputId": "9d911aab-3bc2-42f0-95d6-b0907005e1b9"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "symbol         0\n",
              "date           0\n",
              "close          0\n",
              "high           0\n",
              "low            0\n",
              "open           0\n",
              "volume         0\n",
              "adjClose       0\n",
              "adjHigh        0\n",
              "adjLow         0\n",
              "adjOpen        0\n",
              "adjVolume      0\n",
              "divCash        0\n",
              "splitFactor    0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df[['date','open','close']] # Extracting required columns\n",
        "df['date'] = pd.to_datetime(df['date'].apply(lambda x: x.split()[0])) # converting object dtype of date column to datetime dtype\n",
        "df.set_index('date',drop=True,inplace=True) # Setting date column as index\n",
        "df.head(10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 394
        },
        "id": "jNS17QoaFM8A",
        "outputId": "3e4273d8-7287-4af9-9e7c-1ee8e2a7f374"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "              open   close\n",
              "date                      \n",
              "2016-06-14  716.48  718.27\n",
              "2016-06-15  719.00  718.92\n",
              "2016-06-16  714.91  710.36\n",
              "2016-06-17  708.65  691.72\n",
              "2016-06-20  698.77  693.71\n",
              "2016-06-21  698.40  695.94\n",
              "2016-06-22  699.06  697.46\n",
              "2016-06-23  697.45  701.87\n",
              "2016-06-24  675.17  675.22\n",
              "2016-06-27  671.00  668.26"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7da2bd2a-6eb2-4287-b3d4-b0eb5f233fd1\" 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>open</th>\n",
              "      <th>close</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2016-06-14</th>\n",
              "      <td>716.48</td>\n",
              "      <td>718.27</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-15</th>\n",
              "      <td>719.00</td>\n",
              "      <td>718.92</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-16</th>\n",
              "      <td>714.91</td>\n",
              "      <td>710.36</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-17</th>\n",
              "      <td>708.65</td>\n",
              "      <td>691.72</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-20</th>\n",
              "      <td>698.77</td>\n",
              "      <td>693.71</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-21</th>\n",
              "      <td>698.40</td>\n",
              "      <td>695.94</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-22</th>\n",
              "      <td>699.06</td>\n",
              "      <td>697.46</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-23</th>\n",
              "      <td>697.45</td>\n",
              "      <td>701.87</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-24</th>\n",
              "      <td>675.17</td>\n",
              "      <td>675.22</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-27</th>\n",
              "      <td>671.00</td>\n",
              "      <td>668.26</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-7da2bd2a-6eb2-4287-b3d4-b0eb5f233fd1')\"\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-7da2bd2a-6eb2-4287-b3d4-b0eb5f233fd1 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-7da2bd2a-6eb2-4287-b3d4-b0eb5f233fd1');\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-5286926a-6df1-4627-b793-66306aee9b55\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-5286926a-6df1-4627-b793-66306aee9b55')\"\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-5286926a-6df1-4627-b793-66306aee9b55 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# plotting open and closing price on date index\n",
        "fig, ax =plt.subplots(1,2,figsize=(20,7))\n",
        "ax[0].plot(df['open'],label='Open',color='green')\n",
        "ax[0].set_xlabel('Date',size=15)\n",
        "ax[0].set_ylabel('Price',size=15)\n",
        "ax[0].legend()\n",
        "\n",
        "ax[1].plot(df['close'],label='Close',color='red')\n",
        "ax[1].set_xlabel('Date',size=15)\n",
        "ax[1].set_ylabel('Price',size=15)\n",
        "ax[1].legend()\n",
        "\n",
        "fig.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 455
        },
        "id": "s74q3C5QFRdb",
        "outputId": "c428bda7-eb01-44a8-83f0-eb7b3319bc47"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 2000x700 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Data Pre-processing**"
      ],
      "metadata": {
        "id": "HHFDb7LNFWsB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# normalizing all the values of all columns using MinMaxScaler\n",
        "MMS = MinMaxScaler()\n",
        "df[df.columns] = MMS.fit_transform(df)\n",
        "df.head(10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 394
        },
        "id": "qEgDoe9eFVo6",
        "outputId": "cc8d4573-eb88-46ab-dddf-58a36122a262"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                open     close\n",
              "date                          \n",
              "2016-06-14  0.024532  0.026984\n",
              "2016-06-15  0.025891  0.027334\n",
              "2016-06-16  0.023685  0.022716\n",
              "2016-06-17  0.020308  0.012658\n",
              "2016-06-20  0.014979  0.013732\n",
              "2016-06-21  0.014779  0.014935\n",
              "2016-06-22  0.015135  0.015755\n",
              "2016-06-23  0.014267  0.018135\n",
              "2016-06-24  0.002249  0.003755\n",
              "2016-06-27  0.000000  0.000000"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-2353e408-e0d3-48d9-8a84-e5a268a18dfe\" 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>open</th>\n",
              "      <th>close</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2016-06-14</th>\n",
              "      <td>0.024532</td>\n",
              "      <td>0.026984</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-15</th>\n",
              "      <td>0.025891</td>\n",
              "      <td>0.027334</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-16</th>\n",
              "      <td>0.023685</td>\n",
              "      <td>0.022716</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-17</th>\n",
              "      <td>0.020308</td>\n",
              "      <td>0.012658</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-20</th>\n",
              "      <td>0.014979</td>\n",
              "      <td>0.013732</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-21</th>\n",
              "      <td>0.014779</td>\n",
              "      <td>0.014935</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-22</th>\n",
              "      <td>0.015135</td>\n",
              "      <td>0.015755</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-23</th>\n",
              "      <td>0.014267</td>\n",
              "      <td>0.018135</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-24</th>\n",
              "      <td>0.002249</td>\n",
              "      <td>0.003755</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-27</th>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</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-2353e408-e0d3-48d9-8a84-e5a268a18dfe')\"\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-2353e408-e0d3-48d9-8a84-e5a268a18dfe 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-2353e408-e0d3-48d9-8a84-e5a268a18dfe');\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-3d404965-a515-4e77-b6de-4c5377719765\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-3d404965-a515-4e77-b6de-4c5377719765')\"\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-3d404965-a515-4e77-b6de-4c5377719765 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# splitting the data into training and test set\n",
        "training_size = round(len(df) * 0.75) # Selecting 75 % for training and 25 % for testing\n",
        "training_size"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j9dJFRBDFWF6",
        "outputId": "7c307e43-94ee-4048-f9fb-f91d5450d069"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "944"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_data = df[:training_size]\n",
        "test_data  = df[training_size:]\n",
        "\n",
        "train_data.shape, test_data.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Vw7Th3S2Fdjc",
        "outputId": "d7dba7a7-a418-4c73-dee8-cf9cf780e4bb"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "((944, 2), (314, 2))"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Function to create sequence of data for training and testing\n",
        "\n",
        "def create_sequence(dataset):\n",
        "  sequences = []\n",
        "  labels = []\n",
        "\n",
        "  start_idx = 0\n",
        "\n",
        "  for stop_idx in range(50,len(dataset)): # Selecting 50 rows at a time\n",
        "    sequences.append(dataset.iloc[start_idx:stop_idx])\n",
        "    labels.append(dataset.iloc[stop_idx])\n",
        "    start_idx += 1\n",
        "  return (np.array(sequences),np.array(labels))"
      ],
      "metadata": {
        "id": "oqSADjXRFg4d"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "train_seq, train_label = create_sequence(train_data)\n",
        "test_seq, test_label = create_sequence(test_data)\n",
        "train_seq.shape, train_label.shape, test_seq.shape, test_label.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VrHuoZ9DFiR1",
        "outputId": "8e5dab02-0955-4b2c-ddea-05e66b3a92d1"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "((894, 50, 2), (894, 2), (264, 50, 2), (264, 2))"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Creating LSTM Model**"
      ],
      "metadata": {
        "id": "X-9ovp2jFkfN"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# imported Sequential from keras.models\n",
        "model = Sequential()\n",
        "# importing Dense, Dropout, LSTM, Bidirectional from keras.layers\n",
        "model.add(LSTM(units=50, return_sequences=True, input_shape = (train_seq.shape[1], train_seq.shape[2])))\n",
        "\n",
        "model.add(Dropout(0.1))\n",
        "model.add(LSTM(units=50))\n",
        "\n",
        "model.add(Dense(2))\n",
        "\n",
        "model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mean_absolute_error'])\n",
        "\n",
        "model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "G6VhgVRRFnkH",
        "outputId": "725c308b-f1d5-4751-af8d-c550a3bfe801"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " lstm (LSTM)                 (None, 50, 50)            10600     \n",
            "                                                                 \n",
            " dropout (Dropout)           (None, 50, 50)            0         \n",
            "                                                                 \n",
            " lstm_1 (LSTM)               (None, 50)                20200     \n",
            "                                                                 \n",
            " dense (Dense)               (None, 2)                 102       \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 30902 (120.71 KB)\n",
            "Trainable params: 30902 (120.71 KB)\n",
            "Non-trainable params: 0 (0.00 Byte)\n",
            "_________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# fitting the model by iterating the dataset over 100 times(100 epochs)\n",
        "model.fit(train_seq, train_label, epochs=100,validation_data=(test_seq, test_label), verbose=1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ptzttONxFrBe",
        "outputId": "5e93b566-d039-4780-ea47-a9961aae2eca"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "28/28 [==============================] - 8s 108ms/step - loss: 0.0071 - mean_absolute_error: 0.0606 - val_loss: 0.0169 - val_mean_absolute_error: 0.1045\n",
            "Epoch 2/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 8.6853e-04 - mean_absolute_error: 0.0234 - val_loss: 0.0074 - val_mean_absolute_error: 0.0678\n",
            "Epoch 3/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 4.3962e-04 - mean_absolute_error: 0.0155 - val_loss: 0.0052 - val_mean_absolute_error: 0.0562\n",
            "Epoch 4/100\n",
            "28/28 [==============================] - 2s 54ms/step - loss: 4.0847e-04 - mean_absolute_error: 0.0148 - val_loss: 0.0041 - val_mean_absolute_error: 0.0485\n",
            "Epoch 5/100\n",
            "28/28 [==============================] - 2s 59ms/step - loss: 4.2207e-04 - mean_absolute_error: 0.0149 - val_loss: 0.0049 - val_mean_absolute_error: 0.0542\n",
            "Epoch 6/100\n",
            "28/28 [==============================] - 2s 83ms/step - loss: 4.1090e-04 - mean_absolute_error: 0.0147 - val_loss: 0.0054 - val_mean_absolute_error: 0.0575\n",
            "Epoch 7/100\n",
            "28/28 [==============================] - 2s 86ms/step - loss: 3.7722e-04 - mean_absolute_error: 0.0142 - val_loss: 0.0048 - val_mean_absolute_error: 0.0537\n",
            "Epoch 8/100\n",
            "28/28 [==============================] - 2s 63ms/step - loss: 3.8559e-04 - mean_absolute_error: 0.0143 - val_loss: 0.0049 - val_mean_absolute_error: 0.0548\n",
            "Epoch 9/100\n",
            "28/28 [==============================] - 3s 107ms/step - loss: 3.5721e-04 - mean_absolute_error: 0.0139 - val_loss: 0.0042 - val_mean_absolute_error: 0.0498\n",
            "Epoch 10/100\n",
            "28/28 [==============================] - 2s 81ms/step - loss: 3.6375e-04 - mean_absolute_error: 0.0138 - val_loss: 0.0048 - val_mean_absolute_error: 0.0543\n",
            "Epoch 11/100\n",
            "28/28 [==============================] - 2s 63ms/step - loss: 3.6151e-04 - mean_absolute_error: 0.0139 - val_loss: 0.0054 - val_mean_absolute_error: 0.0596\n",
            "Epoch 12/100\n",
            "28/28 [==============================] - 3s 123ms/step - loss: 3.6255e-04 - mean_absolute_error: 0.0137 - val_loss: 0.0042 - val_mean_absolute_error: 0.0505\n",
            "Epoch 13/100\n",
            "28/28 [==============================] - 3s 97ms/step - loss: 3.3351e-04 - mean_absolute_error: 0.0132 - val_loss: 0.0044 - val_mean_absolute_error: 0.0527\n",
            "Epoch 14/100\n",
            "28/28 [==============================] - 3s 93ms/step - loss: 3.3856e-04 - mean_absolute_error: 0.0134 - val_loss: 0.0057 - val_mean_absolute_error: 0.0618\n",
            "Epoch 15/100\n",
            "28/28 [==============================] - 2s 85ms/step - loss: 3.2153e-04 - mean_absolute_error: 0.0133 - val_loss: 0.0037 - val_mean_absolute_error: 0.0479\n",
            "Epoch 16/100\n",
            "28/28 [==============================] - 2s 84ms/step - loss: 3.2474e-04 - mean_absolute_error: 0.0130 - val_loss: 0.0063 - val_mean_absolute_error: 0.0660\n",
            "Epoch 17/100\n",
            "28/28 [==============================] - 2s 77ms/step - loss: 3.6940e-04 - mean_absolute_error: 0.0142 - val_loss: 0.0023 - val_mean_absolute_error: 0.0358\n",
            "Epoch 18/100\n",
            "28/28 [==============================] - 3s 123ms/step - loss: 3.0811e-04 - mean_absolute_error: 0.0130 - val_loss: 0.0036 - val_mean_absolute_error: 0.0464\n",
            "Epoch 19/100\n",
            "28/28 [==============================] - 2s 54ms/step - loss: 3.1697e-04 - mean_absolute_error: 0.0129 - val_loss: 0.0058 - val_mean_absolute_error: 0.0621\n",
            "Epoch 20/100\n",
            "28/28 [==============================] - 2s 77ms/step - loss: 3.7269e-04 - mean_absolute_error: 0.0141 - val_loss: 0.0037 - val_mean_absolute_error: 0.0475\n",
            "Epoch 21/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 3.2448e-04 - mean_absolute_error: 0.0133 - val_loss: 0.0044 - val_mean_absolute_error: 0.0530\n",
            "Epoch 22/100\n",
            "28/28 [==============================] - 1s 51ms/step - loss: 2.7636e-04 - mean_absolute_error: 0.0122 - val_loss: 0.0038 - val_mean_absolute_error: 0.0483\n",
            "Epoch 23/100\n",
            "28/28 [==============================] - 2s 54ms/step - loss: 2.8553e-04 - mean_absolute_error: 0.0123 - val_loss: 0.0042 - val_mean_absolute_error: 0.0514\n",
            "Epoch 24/100\n",
            "28/28 [==============================] - 5s 173ms/step - loss: 2.6103e-04 - mean_absolute_error: 0.0116 - val_loss: 0.0057 - val_mean_absolute_error: 0.0620\n",
            "Epoch 25/100\n",
            "28/28 [==============================] - 3s 110ms/step - loss: 3.0876e-04 - mean_absolute_error: 0.0130 - val_loss: 0.0027 - val_mean_absolute_error: 0.0390\n",
            "Epoch 26/100\n",
            "28/28 [==============================] - 3s 116ms/step - loss: 2.8044e-04 - mean_absolute_error: 0.0123 - val_loss: 0.0034 - val_mean_absolute_error: 0.0455\n",
            "Epoch 27/100\n",
            "28/28 [==============================] - 3s 111ms/step - loss: 2.4918e-04 - mean_absolute_error: 0.0116 - val_loss: 0.0044 - val_mean_absolute_error: 0.0531\n",
            "Epoch 28/100\n",
            "28/28 [==============================] - 3s 100ms/step - loss: 2.5898e-04 - mean_absolute_error: 0.0118 - val_loss: 0.0049 - val_mean_absolute_error: 0.0562\n",
            "Epoch 29/100\n",
            "28/28 [==============================] - 2s 58ms/step - loss: 2.5297e-04 - mean_absolute_error: 0.0115 - val_loss: 0.0045 - val_mean_absolute_error: 0.0532\n",
            "Epoch 30/100\n",
            "28/28 [==============================] - 1s 54ms/step - loss: 2.4424e-04 - mean_absolute_error: 0.0114 - val_loss: 0.0035 - val_mean_absolute_error: 0.0452\n",
            "Epoch 31/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 2.3970e-04 - mean_absolute_error: 0.0114 - val_loss: 0.0037 - val_mean_absolute_error: 0.0468\n",
            "Epoch 32/100\n",
            "28/28 [==============================] - 2s 54ms/step - loss: 2.5488e-04 - mean_absolute_error: 0.0119 - val_loss: 0.0034 - val_mean_absolute_error: 0.0453\n",
            "Epoch 33/100\n",
            "28/28 [==============================] - 2s 70ms/step - loss: 2.3268e-04 - mean_absolute_error: 0.0113 - val_loss: 0.0036 - val_mean_absolute_error: 0.0461\n",
            "Epoch 34/100\n",
            "28/28 [==============================] - 3s 90ms/step - loss: 2.4903e-04 - mean_absolute_error: 0.0117 - val_loss: 0.0014 - val_mean_absolute_error: 0.0271\n",
            "Epoch 35/100\n",
            "28/28 [==============================] - 3s 118ms/step - loss: 2.4755e-04 - mean_absolute_error: 0.0116 - val_loss: 0.0029 - val_mean_absolute_error: 0.0408\n",
            "Epoch 36/100\n",
            "28/28 [==============================] - 2s 69ms/step - loss: 2.3330e-04 - mean_absolute_error: 0.0112 - val_loss: 0.0024 - val_mean_absolute_error: 0.0359\n",
            "Epoch 37/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 2.3493e-04 - mean_absolute_error: 0.0112 - val_loss: 0.0025 - val_mean_absolute_error: 0.0377\n",
            "Epoch 38/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 2.2700e-04 - mean_absolute_error: 0.0111 - val_loss: 0.0044 - val_mean_absolute_error: 0.0539\n",
            "Epoch 39/100\n",
            "28/28 [==============================] - 3s 110ms/step - loss: 2.3387e-04 - mean_absolute_error: 0.0112 - val_loss: 0.0051 - val_mean_absolute_error: 0.0579\n",
            "Epoch 40/100\n",
            "28/28 [==============================] - 5s 165ms/step - loss: 2.2346e-04 - mean_absolute_error: 0.0110 - val_loss: 0.0019 - val_mean_absolute_error: 0.0321\n",
            "Epoch 41/100\n",
            "28/28 [==============================] - 3s 113ms/step - loss: 2.1268e-04 - mean_absolute_error: 0.0105 - val_loss: 0.0025 - val_mean_absolute_error: 0.0376\n",
            "Epoch 42/100\n",
            "28/28 [==============================] - 3s 110ms/step - loss: 2.1086e-04 - mean_absolute_error: 0.0104 - val_loss: 0.0032 - val_mean_absolute_error: 0.0433\n",
            "Epoch 43/100\n",
            "28/28 [==============================] - 3s 91ms/step - loss: 1.9940e-04 - mean_absolute_error: 0.0104 - val_loss: 0.0014 - val_mean_absolute_error: 0.0275\n",
            "Epoch 44/100\n",
            "28/28 [==============================] - 3s 122ms/step - loss: 2.0808e-04 - mean_absolute_error: 0.0105 - val_loss: 0.0043 - val_mean_absolute_error: 0.0532\n",
            "Epoch 45/100\n",
            "28/28 [==============================] - 3s 112ms/step - loss: 2.0495e-04 - mean_absolute_error: 0.0106 - val_loss: 0.0028 - val_mean_absolute_error: 0.0411\n",
            "Epoch 46/100\n",
            "28/28 [==============================] - 2s 88ms/step - loss: 1.9508e-04 - mean_absolute_error: 0.0102 - val_loss: 0.0019 - val_mean_absolute_error: 0.0334\n",
            "Epoch 47/100\n",
            "28/28 [==============================] - 3s 91ms/step - loss: 2.1550e-04 - mean_absolute_error: 0.0106 - val_loss: 0.0022 - val_mean_absolute_error: 0.0364\n",
            "Epoch 48/100\n",
            "28/28 [==============================] - 3s 93ms/step - loss: 2.1183e-04 - mean_absolute_error: 0.0108 - val_loss: 0.0037 - val_mean_absolute_error: 0.0504\n",
            "Epoch 49/100\n",
            "28/28 [==============================] - 3s 121ms/step - loss: 1.9310e-04 - mean_absolute_error: 0.0101 - val_loss: 0.0023 - val_mean_absolute_error: 0.0359\n",
            "Epoch 50/100\n",
            "28/28 [==============================] - 2s 79ms/step - loss: 1.9051e-04 - mean_absolute_error: 0.0100 - val_loss: 0.0025 - val_mean_absolute_error: 0.0373\n",
            "Epoch 51/100\n",
            "28/28 [==============================] - 2s 75ms/step - loss: 1.8038e-04 - mean_absolute_error: 0.0095 - val_loss: 0.0029 - val_mean_absolute_error: 0.0426\n",
            "Epoch 52/100\n",
            "28/28 [==============================] - 2s 56ms/step - loss: 1.7848e-04 - mean_absolute_error: 0.0097 - val_loss: 0.0013 - val_mean_absolute_error: 0.0259\n",
            "Epoch 53/100\n",
            "28/28 [==============================] - 2s 79ms/step - loss: 1.7987e-04 - mean_absolute_error: 0.0097 - val_loss: 0.0028 - val_mean_absolute_error: 0.0410\n",
            "Epoch 54/100\n",
            "28/28 [==============================] - 2s 89ms/step - loss: 1.7737e-04 - mean_absolute_error: 0.0095 - val_loss: 0.0033 - val_mean_absolute_error: 0.0463\n",
            "Epoch 55/100\n",
            "28/28 [==============================] - 4s 125ms/step - loss: 1.8464e-04 - mean_absolute_error: 0.0099 - val_loss: 0.0012 - val_mean_absolute_error: 0.0255\n",
            "Epoch 56/100\n",
            "28/28 [==============================] - 2s 77ms/step - loss: 1.6386e-04 - mean_absolute_error: 0.0092 - val_loss: 0.0011 - val_mean_absolute_error: 0.0245\n",
            "Epoch 57/100\n",
            "28/28 [==============================] - 2s 85ms/step - loss: 1.7082e-04 - mean_absolute_error: 0.0095 - val_loss: 0.0027 - val_mean_absolute_error: 0.0412\n",
            "Epoch 58/100\n",
            "28/28 [==============================] - 2s 57ms/step - loss: 1.8443e-04 - mean_absolute_error: 0.0097 - val_loss: 9.4898e-04 - val_mean_absolute_error: 0.0225\n",
            "Epoch 59/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 2.0423e-04 - mean_absolute_error: 0.0103 - val_loss: 9.6271e-04 - val_mean_absolute_error: 0.0225\n",
            "Epoch 60/100\n",
            "28/28 [==============================] - 2s 55ms/step - loss: 1.8446e-04 - mean_absolute_error: 0.0099 - val_loss: 6.6327e-04 - val_mean_absolute_error: 0.0189\n",
            "Epoch 61/100\n",
            "28/28 [==============================] - 3s 106ms/step - loss: 1.8569e-04 - mean_absolute_error: 0.0100 - val_loss: 8.5859e-04 - val_mean_absolute_error: 0.0214\n",
            "Epoch 62/100\n",
            "28/28 [==============================] - 3s 89ms/step - loss: 1.7904e-04 - mean_absolute_error: 0.0098 - val_loss: 8.4858e-04 - val_mean_absolute_error: 0.0213\n",
            "Epoch 63/100\n",
            "28/28 [==============================] - 1s 54ms/step - loss: 1.5489e-04 - mean_absolute_error: 0.0088 - val_loss: 0.0026 - val_mean_absolute_error: 0.0408\n",
            "Epoch 64/100\n",
            "28/28 [==============================] - 2s 54ms/step - loss: 1.5464e-04 - mean_absolute_error: 0.0090 - val_loss: 0.0013 - val_mean_absolute_error: 0.0271\n",
            "Epoch 65/100\n",
            "28/28 [==============================] - 3s 107ms/step - loss: 1.5422e-04 - mean_absolute_error: 0.0088 - val_loss: 0.0017 - val_mean_absolute_error: 0.0307\n",
            "Epoch 66/100\n",
            "28/28 [==============================] - 3s 112ms/step - loss: 1.6889e-04 - mean_absolute_error: 0.0094 - val_loss: 0.0011 - val_mean_absolute_error: 0.0243\n",
            "Epoch 67/100\n",
            "28/28 [==============================] - 2s 82ms/step - loss: 1.5886e-04 - mean_absolute_error: 0.0091 - val_loss: 0.0010 - val_mean_absolute_error: 0.0230\n",
            "Epoch 68/100\n",
            "28/28 [==============================] - 1s 51ms/step - loss: 1.6267e-04 - mean_absolute_error: 0.0092 - val_loss: 0.0011 - val_mean_absolute_error: 0.0238\n",
            "Epoch 69/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 1.4366e-04 - mean_absolute_error: 0.0087 - val_loss: 0.0010 - val_mean_absolute_error: 0.0230\n",
            "Epoch 70/100\n",
            "28/28 [==============================] - 1s 52ms/step - loss: 1.3641e-04 - mean_absolute_error: 0.0083 - val_loss: 0.0019 - val_mean_absolute_error: 0.0335\n",
            "Epoch 71/100\n",
            "28/28 [==============================] - 2s 86ms/step - loss: 1.4025e-04 - mean_absolute_error: 0.0083 - val_loss: 0.0017 - val_mean_absolute_error: 0.0330\n",
            "Epoch 72/100\n",
            "28/28 [==============================] - 2s 71ms/step - loss: 1.2938e-04 - mean_absolute_error: 0.0082 - val_loss: 0.0011 - val_mean_absolute_error: 0.0243\n",
            "Epoch 73/100\n",
            "28/28 [==============================] - 2s 68ms/step - loss: 1.3647e-04 - mean_absolute_error: 0.0083 - val_loss: 0.0011 - val_mean_absolute_error: 0.0244\n",
            "Epoch 74/100\n",
            "28/28 [==============================] - 3s 109ms/step - loss: 1.2955e-04 - mean_absolute_error: 0.0080 - val_loss: 0.0013 - val_mean_absolute_error: 0.0269\n",
            "Epoch 75/100\n",
            "28/28 [==============================] - 2s 63ms/step - loss: 1.3027e-04 - mean_absolute_error: 0.0081 - val_loss: 0.0013 - val_mean_absolute_error: 0.0274\n",
            "Epoch 76/100\n",
            "28/28 [==============================] - 1s 52ms/step - loss: 1.3198e-04 - mean_absolute_error: 0.0082 - val_loss: 0.0013 - val_mean_absolute_error: 0.0265\n",
            "Epoch 77/100\n",
            "28/28 [==============================] - 3s 117ms/step - loss: 1.2527e-04 - mean_absolute_error: 0.0082 - val_loss: 8.4187e-04 - val_mean_absolute_error: 0.0212\n",
            "Epoch 78/100\n",
            "28/28 [==============================] - 4s 148ms/step - loss: 1.2545e-04 - mean_absolute_error: 0.0082 - val_loss: 0.0028 - val_mean_absolute_error: 0.0440\n",
            "Epoch 79/100\n",
            "28/28 [==============================] - 4s 123ms/step - loss: 1.2937e-04 - mean_absolute_error: 0.0082 - val_loss: 9.9537e-04 - val_mean_absolute_error: 0.0233\n",
            "Epoch 80/100\n",
            "28/28 [==============================] - 2s 86ms/step - loss: 1.1880e-04 - mean_absolute_error: 0.0079 - val_loss: 0.0010 - val_mean_absolute_error: 0.0235\n",
            "Epoch 81/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 1.2599e-04 - mean_absolute_error: 0.0079 - val_loss: 0.0018 - val_mean_absolute_error: 0.0332\n",
            "Epoch 82/100\n",
            "28/28 [==============================] - 2s 90ms/step - loss: 1.1656e-04 - mean_absolute_error: 0.0076 - val_loss: 0.0011 - val_mean_absolute_error: 0.0248\n",
            "Epoch 83/100\n",
            "28/28 [==============================] - 4s 157ms/step - loss: 1.2678e-04 - mean_absolute_error: 0.0081 - val_loss: 0.0016 - val_mean_absolute_error: 0.0314\n",
            "Epoch 84/100\n",
            "28/28 [==============================] - 2s 64ms/step - loss: 1.1355e-04 - mean_absolute_error: 0.0078 - val_loss: 6.2653e-04 - val_mean_absolute_error: 0.0181\n",
            "Epoch 85/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 1.2197e-04 - mean_absolute_error: 0.0079 - val_loss: 5.6124e-04 - val_mean_absolute_error: 0.0171\n",
            "Epoch 86/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 1.1406e-04 - mean_absolute_error: 0.0076 - val_loss: 0.0013 - val_mean_absolute_error: 0.0278\n",
            "Epoch 87/100\n",
            "28/28 [==============================] - 1s 52ms/step - loss: 1.3183e-04 - mean_absolute_error: 0.0081 - val_loss: 0.0010 - val_mean_absolute_error: 0.0242\n",
            "Epoch 88/100\n",
            "28/28 [==============================] - 1s 52ms/step - loss: 1.0774e-04 - mean_absolute_error: 0.0074 - val_loss: 0.0015 - val_mean_absolute_error: 0.0305\n",
            "Epoch 89/100\n",
            "28/28 [==============================] - 2s 54ms/step - loss: 1.0162e-04 - mean_absolute_error: 0.0073 - val_loss: 4.8080e-04 - val_mean_absolute_error: 0.0160\n",
            "Epoch 90/100\n",
            "28/28 [==============================] - 2s 60ms/step - loss: 1.1886e-04 - mean_absolute_error: 0.0077 - val_loss: 9.1055e-04 - val_mean_absolute_error: 0.0223\n",
            "Epoch 91/100\n",
            "28/28 [==============================] - 3s 90ms/step - loss: 1.1811e-04 - mean_absolute_error: 0.0076 - val_loss: 0.0011 - val_mean_absolute_error: 0.0253\n",
            "Epoch 92/100\n",
            "28/28 [==============================] - 2s 58ms/step - loss: 1.1746e-04 - mean_absolute_error: 0.0076 - val_loss: 5.0266e-04 - val_mean_absolute_error: 0.0163\n",
            "Epoch 93/100\n",
            "28/28 [==============================] - 2s 81ms/step - loss: 1.2640e-04 - mean_absolute_error: 0.0081 - val_loss: 0.0019 - val_mean_absolute_error: 0.0348\n",
            "Epoch 94/100\n",
            "28/28 [==============================] - 1s 53ms/step - loss: 1.3321e-04 - mean_absolute_error: 0.0082 - val_loss: 6.3548e-04 - val_mean_absolute_error: 0.0183\n",
            "Epoch 95/100\n",
            "28/28 [==============================] - 2s 55ms/step - loss: 1.0631e-04 - mean_absolute_error: 0.0073 - val_loss: 6.1448e-04 - val_mean_absolute_error: 0.0179\n",
            "Epoch 96/100\n",
            "28/28 [==============================] - 2s 55ms/step - loss: 9.3550e-05 - mean_absolute_error: 0.0068 - val_loss: 0.0011 - val_mean_absolute_error: 0.0250\n",
            "Epoch 97/100\n",
            "28/28 [==============================] - 2s 55ms/step - loss: 1.0342e-04 - mean_absolute_error: 0.0071 - val_loss: 0.0013 - val_mean_absolute_error: 0.0265\n",
            "Epoch 98/100\n",
            "28/28 [==============================] - 3s 92ms/step - loss: 9.8662e-05 - mean_absolute_error: 0.0070 - val_loss: 0.0032 - val_mean_absolute_error: 0.0472\n",
            "Epoch 99/100\n",
            "28/28 [==============================] - 2s 66ms/step - loss: 1.2879e-04 - mean_absolute_error: 0.0084 - val_loss: 6.7538e-04 - val_mean_absolute_error: 0.0189\n",
            "Epoch 100/100\n",
            "28/28 [==============================] - 2s 55ms/step - loss: 1.1248e-04 - mean_absolute_error: 0.0075 - val_loss: 6.2508e-04 - val_mean_absolute_error: 0.0181\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.src.callbacks.History at 0x7b69d794fa00>"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# predicting the values after running the model\n",
        "test_predicted = model.predict(test_seq)\n",
        "test_predicted[:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dTnKODsVFv5X",
        "outputId": "c9bb18e1-df7e-4b5b-869f-c5de86c24c3f"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "9/9 [==============================] - 1s 21ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.40628272, 0.40781495],\n",
              "       [0.40558338, 0.40726528],\n",
              "       [0.4026432 , 0.4043056 ],\n",
              "       [0.4080664 , 0.40933156],\n",
              "       [0.41144168, 0.4126533 ]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Inversing normalization/scaling on predicted data\n",
        "test_inverse_predicted = MMS.inverse_transform(test_predicted)\n",
        "test_inverse_predicted[:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PjrPuIJ_FyBf",
        "outputId": "29c265b1-9c60-46d1-c6fc-d8c3b18f1ebd"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[1424.2157, 1424.0797],\n",
              "       [1422.9192, 1423.061 ],\n",
              "       [1417.4683, 1417.5757],\n",
              "       [1427.5225, 1426.8906],\n",
              "       [1433.78  , 1433.0469]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Visualizing Actual Vs Predicted Data**"
      ],
      "metadata": {
        "id": "QxbVc2TNFzhn"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Merging actual and predicted data for better visualization\n",
        "df_merge = pd.concat([df.iloc[-264:].copy(),\n",
        "                          pd.DataFrame(test_inverse_predicted,columns=['open_predicted','close_predicted'],\n",
        "                                       index=df.iloc[-264:].index)], axis=1)"
      ],
      "metadata": {
        "id": "aWQTB12BF4UZ"
      },
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Inversing normalization/scaling\n",
        "df_merge[['open','close']] = MMS.inverse_transform(df_merge[['open','close']])\n",
        "df_merge.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 237
        },
        "id": "LVwT-8uZF7RS",
        "outputId": "e2d343a4-d74e-4144-8ef0-fc924a62633e"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "               open    close  open_predicted  close_predicted\n",
              "date                                                         \n",
              "2020-05-27  1417.25  1417.84     1424.215698      1424.079712\n",
              "2020-05-28  1396.86  1416.73     1422.919189      1423.061035\n",
              "2020-05-29  1416.94  1428.92     1417.468262      1417.575684\n",
              "2020-06-01  1418.39  1431.82     1427.522461      1426.890625\n",
              "2020-06-02  1430.55  1439.22     1433.780029      1433.046875"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a81a757f-a5bd-480f-a6ce-61c1556858cc\" 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>open</th>\n",
              "      <th>close</th>\n",
              "      <th>open_predicted</th>\n",
              "      <th>close_predicted</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2020-05-27</th>\n",
              "      <td>1417.25</td>\n",
              "      <td>1417.84</td>\n",
              "      <td>1424.215698</td>\n",
              "      <td>1424.079712</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-05-28</th>\n",
              "      <td>1396.86</td>\n",
              "      <td>1416.73</td>\n",
              "      <td>1422.919189</td>\n",
              "      <td>1423.061035</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-05-29</th>\n",
              "      <td>1416.94</td>\n",
              "      <td>1428.92</td>\n",
              "      <td>1417.468262</td>\n",
              "      <td>1417.575684</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-06-01</th>\n",
              "      <td>1418.39</td>\n",
              "      <td>1431.82</td>\n",
              "      <td>1427.522461</td>\n",
              "      <td>1426.890625</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-06-02</th>\n",
              "      <td>1430.55</td>\n",
              "      <td>1439.22</td>\n",
              "      <td>1433.780029</td>\n",
              "      <td>1433.046875</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-a81a757f-a5bd-480f-a6ce-61c1556858cc')\"\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-a81a757f-a5bd-480f-a6ce-61c1556858cc 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-a81a757f-a5bd-480f-a6ce-61c1556858cc');\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-72e0e7b0-c8e3-4384-a052-afae7d780784\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-72e0e7b0-c8e3-4384-a052-afae7d780784')\"\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-72e0e7b0-c8e3-4384-a052-afae7d780784 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# plotting the actual open and predicted open prices on date index\n",
        "df_merge[['open','open_predicted']].plot(figsize=(10,6))\n",
        "plt.xticks(rotation=45)\n",
        "plt.xlabel('Date',size=15)\n",
        "plt.ylabel('Stock Price',size=15)\n",
        "plt.title('Actual vs Predicted for open price',size=15)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 555
        },
        "id": "fTD-SE4iGBVi",
        "outputId": "d6c158a7-e714-42a6-b3e0-5269805ba148"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# plotting the actual close and predicted close prices on date index\n",
        "df_merge[['close','close_predicted']].plot(figsize=(10,6))\n",
        "plt.xticks(rotation=45)\n",
        "plt.xlabel('Date',size=15)\n",
        "plt.ylabel('Stock Price',size=15)\n",
        "plt.title('Actual vs Predicted for close price',size=15)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 555
        },
        "id": "4kSOT-wjGDpR",
        "outputId": "1c986aa1-5bd3-4fb1-cd9e-e857c75f40ae"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Predicting the Price for upcoming 10 days**"
      ],
      "metadata": {
        "id": "c0GLWQdXGGkT"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Creating a dataframe and adding 10 days to existing index\n",
        "\n",
        "df_merge = df_merge.append(pd.DataFrame(columns=df_merge.columns,\n",
        "                                        index=pd.date_range(start=df_merge.index[-1], periods=11, freq='D', closed='right')))\n",
        "df_merge['2021-06-09':'2021-06-16']"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "l-Sfdu2RGFjp",
        "outputId": "74508cde-ace9-476d-d19c-f7e3b5a95033"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "               open    close  open_predicted  close_predicted\n",
              "2021-06-09  2499.50  2491.40     2389.605713      2403.335938\n",
              "2021-06-10  2494.01  2521.60     2394.841064      2409.458740\n",
              "2021-06-11  2524.92  2513.93     2414.377441      2428.960693\n",
              "2021-06-12      NaN      NaN             NaN              NaN\n",
              "2021-06-13      NaN      NaN             NaN              NaN\n",
              "2021-06-14      NaN      NaN             NaN              NaN\n",
              "2021-06-15      NaN      NaN             NaN              NaN\n",
              "2021-06-16      NaN      NaN             NaN              NaN"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-4c74f000-8109-4aeb-bfc4-da2bc835a54a\" 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>open</th>\n",
              "      <th>close</th>\n",
              "      <th>open_predicted</th>\n",
              "      <th>close_predicted</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2021-06-09</th>\n",
              "      <td>2499.50</td>\n",
              "      <td>2491.40</td>\n",
              "      <td>2389.605713</td>\n",
              "      <td>2403.335938</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2021-06-10</th>\n",
              "      <td>2494.01</td>\n",
              "      <td>2521.60</td>\n",
              "      <td>2394.841064</td>\n",
              "      <td>2409.458740</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2021-06-11</th>\n",
              "      <td>2524.92</td>\n",
              "      <td>2513.93</td>\n",
              "      <td>2414.377441</td>\n",
              "      <td>2428.960693</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2021-06-12</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2021-06-13</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2021-06-14</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2021-06-15</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2021-06-16</th>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4c74f000-8109-4aeb-bfc4-da2bc835a54a')\"\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-4c74f000-8109-4aeb-bfc4-da2bc835a54a 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-4c74f000-8109-4aeb-bfc4-da2bc835a54a');\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-839ea815-ba72-4093-93b1-c340230579bd\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-839ea815-ba72-4093-93b1-c340230579bd')\"\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-839ea815-ba72-4093-93b1-c340230579bd button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# creating a DataFrame and filling values of open and close column\n",
        "upcoming_prediction = pd.DataFrame(columns=['open','close'],index=df_merge.index)\n",
        "upcoming_prediction.index=pd.to_datetime(upcoming_prediction.index)"
      ],
      "metadata": {
        "id": "_FC8Zr24GRlh"
      },
      "execution_count": 25,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "curr_seq = test_seq[-1:]\n",
        "\n",
        "for i in range(-10,0):\n",
        "  up_pred = model.predict(curr_seq)\n",
        "  upcoming_prediction.iloc[i] = up_pred\n",
        "  curr_seq = np.append(curr_seq[0][1:],up_pred,axis=0)\n",
        "  curr_seq = curr_seq.reshape(test_seq[-1:].shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jOGTMUQTGTei",
        "outputId": "6cd8f4d9-62f3-4779-ee9b-0e2ae80723ae"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 28ms/step\n",
            "1/1 [==============================] - 0s 26ms/step\n",
            "1/1 [==============================] - 0s 29ms/step\n",
            "1/1 [==============================] - 0s 28ms/step\n",
            "1/1 [==============================] - 0s 27ms/step\n",
            "1/1 [==============================] - 0s 26ms/step\n",
            "1/1 [==============================] - 0s 35ms/step\n",
            "1/1 [==============================] - 0s 30ms/step\n",
            "1/1 [==============================] - 0s 32ms/step\n",
            "1/1 [==============================] - 0s 28ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# inversing Normalization/scaling\n",
        "upcoming_prediction[['open','close']] = MMS.inverse_transform(upcoming_prediction[['open','close']])"
      ],
      "metadata": {
        "id": "7Ff8YwkoGWQ7"
      },
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# plotting Upcoming Open price on date index\n",
        "fig,ax=plt.subplots(figsize=(10,5))\n",
        "ax.plot(df_merge.loc['2021-04-01':,'open'],label='Current Open Price')\n",
        "ax.plot(upcoming_prediction.loc['2021-04-01':,'open'],label='Upcoming Open Price')\n",
        "plt.setp(ax.xaxis.get_majorticklabels(), rotation=45)\n",
        "ax.set_xlabel('Date',size=15)\n",
        "ax.set_ylabel('Stock Price',size=15)\n",
        "ax.set_title('Upcoming Open price prediction',size=15)\n",
        "ax.legend()\n",
        "fig.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 548
        },
        "id": "crQb6zMwGX6q",
        "outputId": "904b6582-48ad-4f9f-b9fb-825ee3b009ee"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# plotting Upcoming Close price on date index\n",
        "fig,ax=plt.subplots(figsize=(10,5))\n",
        "ax.plot(df_merge.loc['2021-04-01':,'close'],label='Current close Price')\n",
        "ax.plot(upcoming_prediction.loc['2021-04-01':,'close'],label='Upcoming close Price')\n",
        "plt.setp(ax.xaxis.get_majorticklabels(), rotation=45)\n",
        "ax.set_xlabel('Date',size=15)\n",
        "ax.set_ylabel('Stock Price',size=15)\n",
        "ax.set_title('Upcoming close price prediction',size=15)\n",
        "ax.legend()\n",
        "fig.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 548
        },
        "id": "Cal0nZ4SGa4j",
        "outputId": "3e0224ca-6a7b-4810-b155-057a2d3d4560"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2EAAAITCAYAAACOkRRBAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAC3lElEQVR4nOzdd3xTZRfA8V+S7r0HtEDZlFkoYNnIKAoCgiBDpqhgK4K+iKiv4sS9FV9FAQcIKoiCjLL3ppQCZbYUKKWlpXsn9/0jNFLaQnc6zvfzySfNvc+999yQhJw8zz2PSlEUBSGEEEIIIYQQVUJt7ACEEEIIIYQQoi6RJEwIIYQQQgghqpAkYUIIIYQQQghRhSQJE0IIIYQQQogqJEmYEEIIIYQQQlQhScKEEEIIIYQQogpJEiaEEEIIIYQQVUiSMCGEEEIIIYSoQpKECSGEEEIIIUQVkiRMCFGjREVFoVKpUKlUd203efJkVCoV8+fPr5rAqplGjRrd8zmqCebPn49KpWLJkiXGDqXayX+Nb9++3dih1DgqlYpGjRoVWLZ9+3ZUKhWTJ0+u1GP36dMHlUpFVFRUpR5HCFG9SRImhBBCCFFBikrwhBDiTibGDkAIIUTF27JlC7m5ucYOQ1SiBQsW8OKLL9KgQQNjh1IrdOnShdOnT2Nvb1+px/nxxx/JyMigfv36lXocIUT1JkmYEELUQk2aNDF2CKKSeXp64unpaewwag0rKytatmxZ6ceRpFkIATIcUQhRx9x+PcbPP/9Mp06dsLKyws3NjUmTJnH16tVit92wYQNDhw7F3d0dc3NzvL29GTJkCH/88UehtqdOnWL8+PF4enpiZmZG/fr1mThxImfOnCnU9vZrUeLi4nj88cfx8PDA2tqaHj16sHfvXkPbb775hnbt2mFpaYm3tzfz589Hp9MV2mdR14TlX0/Xp08fMjMzefHFF2nYsCHm5uY0bdqU9957D0VRijz3HTt2cP/992Nra4ujoyMPPvgghw8fZsmSJWW69u7y5cvMnDmT5s2bY2lpiZOTE/7+/rz++uukpKSUaB8JCQnMmTOHZs2aYWFhgZOTE4MGDWLTpk1Ftr906RIzZsygefPmWFlZ4eTkROvWrXnqqaeK/He5fPkywcHBNGnSxLD/IUOGFPj3KInbr91av349PXr0wMbGBkdHR0aMGEFEREShbW5/Xs+ePcuYMWNwd3dHrVbz559/FtrvndLT03nvvffw9/fHzs4Oa2trWrZsSVBQEGfPni3U/sCBA4waNcrwevXy8mLatGlER0eX6lzzX3eKovDZZ5/h6+uLhYUF9evXZ+bMmSQlJd31+dm4cSN9+/bFwcEBlUpVoP2GDRsYPHgwrq6umJub07hxY5577jkSEhKKjCUxMZHg4GDq1auHhYUFvr6+fPbZZ8W+xu91Tdi93v/5/2agf63lX7ua/57Ld7drwsr6uZGYmMiMGTPw9PTE3NycNm3a8MMPPxR5HkKIakIRQogaJDIyUgGUe318TZo0SQGU1157rcDy3r17K4ASFBSkqFQqpVevXsqYMWOURo0aKYDi5eWlXL58udD+nnvuOQVQ1Gq10r17d2Xs2LFK7969FQcHB6V9+/YF2m7evFmxtLRUAMXPz08ZM2aM0qFDBwVQbGxslJ07dxZov23bNgVQhg4dqjRu3Fhp2LCh8uijjypdu3ZVAMXKykoJDw9XZs6cqVhaWioPPvigMmTIEMXW1lYBlJdeeqlQvA0bNiz0HOU/dwEBAUqPHj0UJycnZcSIEUpgYKBiYWGhAMrLL79caF9//PGHotFoFEC57777lDFjxiitW7dWzM3NlenTpxf5PN/Nzp07FQcHBwVQGjVqpIwaNUoZMmSI0rRpUwVQjh07Zmj72muvKYCyePHiAvu4cuWK0rhxYwVQGjRooDz66KPK/fffb4jz448/LtA+OjpacXJyUgClWbNmysiRI5Xhw4crfn5+ikqlKrT/vXv3Ko6OjgqgtGjRQhkxYoTSs2dPxcTERNFoNMqvv/5a4vPNfy0+/fTTikqlUjp37qyMGTNG8fX1VQDF3t5eCQ0NLbDN4sWLFUAZM2aMYmdnp/j4+CiPPvqoMnDgQGXt2rUF9rtt27YC28bExCitW7dWAMXR0VF56KGHlEceeUTp2LGjolarlU8++aRA+6+++kpRq9WKWq1WunbtqowaNUpp166dAiiurq7KqVOnSnyu+a+7oKAgxdTUVBkwYIAyevRoxd3dXQGUdu3aKcnJyUU+P0888USB56dz585KUlKSoiiKMnfuXAVQzMzMlO7duyuPPPKI0qxZMwVQmjRposTGxhbYZ2JiotKqVSsFUDw8PJTRo0cr/fv3V0xMTJTg4GAFUBo2bFhgm/z34aRJkwqdV0ne/7t27TKci7W1tTJp0iTDbcGCBYZ95X8GRUZGFjhGWT83hg0bpjRv3lypV6+eMmrUKKVv376G98F3331X4n87IUTVkiRMCFGjVFQSZmJioqxbt86wPCcnRxk/frzhS83tfvrpJwVQ6tWrVyBBUBRFycjIUDZt2mR4nJaWZvjC+eWXXxZo+/HHHxsSvczMTMPy/C9TgPLYY48pOTk5hnX5SYivr69Sr1495fz584Z1J0+eVMzMzBQrKyslNTW1wLHuloQBSu/evQt8GT506JCi0WgK7Ss5OdmQvPzyyy8F9vff//7XsL+SJmEJCQmKq6urAigffPCBotVqC6zfu3evcv369ULnf2eSNGTIEAVQxo0bp2RnZxuW79q1S7GyslI0Gk2Bf6tXX31VAZTg4OBCMV26dKnA85qcnKx4enoqGo1G+fnnnwu0PXTokOLo6KjY2NgocXFxJTrn/NcioHz77beG5TqdzpBcdOjQocA2+UlYfsx5eXnF7vfOJKxfv34KoIwePbrQ6yIyMlI5fvy44fG+ffsUjUaj1K9fXzl8+HCBtosWLVIApWvXriU6T0X593VnZ2dXYH+pqanK/fffrwDKs88+W+R5AEUmtytXrlQApU2bNsq5c+cMy3U6neHf9dFHHy2wTf6PA4MGDVLS09MNyw8cOKDY2NiUKgkrzftfUZQi9327opKw8n5ujBkzRsnKyjKsW716teEHCiFE9SRJmBCiRqmoJGzcuHGFtrlx44ZiZWWlqFQqJTo62rA8/xf1kvR+/PDDD4bepqJ06tRJAQp8uc//MmVnZ6ckJiYWaJ+UlKSoVCoFUBYtWlRofw8//HCRX8TvloSp1WolIiKi0L7yE5vb9/Xdd98pgNKvX79C7XNzcw3HKWkS9t577xm+HJdEUUnYhQsXDL0DCQkJhbbJ77WYNm2aYdmMGTMUQPnzzz/vecxPPvlEAZTnn3++yPX5X4rv7G0rTv5rsVu3boXW5eTkKF5eXgqg7Nq1y7A8PwlzdXUtkEQUtd/b/70OHDigAIqbm5uSkpJyz9iGDRumAMrff/9d5PqhQ4cqgHL06NF77ktR/n3dFdU7e/LkSUWlUik2NjYFkon88xg8eHCR+2zfvr0CKCdOnCi0TqfTKR06dFA0Go0SHx+vKIo+obG0tFTUanWB5DpffuJb0iSsNO9/RSlbElbez40bN24U2qZNmzZF9rgJIaoHuSZMCFEnjRkzptAyZ2dnBg4ciKIo7N69G4CYmBhOnz6Ng4MDo0ePvud+d+3aBcD48eOLXP/YY48VaHc7f39/HB0dCyyzt7fHyckJgIEDBxbapnHjxgBcu3btnrHla9iwIS1atCi0vHnz5oX2tWfPHgBGjRpVqL2JiQkjR44s8XEBNm/eDMBTTz1Vqu1ul/9vM2jQIMNzc7sJEyYABZ/jTp06AfDSSy+xdu1asrKyit1//jVlI0aMKHJ9z549ATh48GCp4i7qNWdqasojjzxSKN58/fv3x8rKqsTHyH9+x44di62t7V3b6nQ6tmzZgpWVFYGBgUW2qchz9fX1pX379qSlpXHs2LFC64cOHVpoWVxcHMePH6dZs2a0adOm0HqVSkX37t3RarUcOXIEgCNHjpCZmYm/v3+RBWrGjh1b4vMo7fu/rMrzudGpUyecnZ0LLS/q/SyEqD6kOqIQokYp6QTEyq2L74tr37BhwyKX58/vExMTA+iLM4A+2SnJsfO3K26eoPzlRRUAKa5ktY2NDQkJCUWut7GxASA7O/ueseXz8vIqcnn+l/bb95X/Bc7b27vIbUpb6S3/+SxP9cayPMeTJ09m06ZNrFy5koceeggLCws6d+7MoEGDmDp1Kh4eHoa2+QUTunfvftc4bty4Uaq4S/qau11lPr83btwgLS0NADMzs3u2LY27nWtoaGiJzzX/3+LcuXP3fP/lx5i/73s93yVR2vd/WZXnc6M072chRPUhSZgQoka5vVcgIyOj2F6CjIwMAKytraskrpK62xc5tfrugxPutb6kKmo/1VVRz7FGo2HFihW8+OKLrFmzhq1bt3LgwAF27drFu+++y4YNG+jWrRuAodrkI488ctfXT1WUM7ewsKi0feefp42NzT17NFu3bl1pceQr6lzzY/Tw8Ci2ty5fcUlXbVCezw0hRPUkSZgQokZxcnLC0tKSzMxMLl68WOQQJYCLFy8Cxf9KfOnSJdq1a1fkcoB69eoB//YAXbx4EUVR7vlreP52+fu5U/4v+zVlotb8eajyewTuVNzy4nh7exMREcGFCxdo27ZtmWIqz3Ps5+eHn58f8+fPJyUlhfnz5/PJJ58wa9Ysw5A7Ly8vzpw5w4svvmgYxlgRiov3ztdceeS/Xi9cuHDPti4uLlhYWKBWq1m8eHGF9vRcunSpyH/f0p5r/vvXxcWFJUuWlGib/NfsvZ7vkijt+7+satvnhhDi3uTnEyFEjaLRaAzDxNatW1dkm8uXLxMaGoparS52SNnKlSsLLUtMTGTTpk2G60xA/+WoVatWJCUl8dtvv90zvvxraJYvX17k+p9//rlAu+ou/3koai40rVbLqlWrSrW//v37A/Dtt9+WOaYePXoA+nmbipp3qqTPsZ2dHQsWLEClUhEeHm5YPmDAAABWr15d5hiLUtRrLi8vz/Dc5p9XeeQ/v8uXLzcMNSyOiYkJffr0ISUlhS1btpT72Lcr6lwjIiIIDQ3FxsaGDh06lGg/Xl5etGzZklOnThU5v1lROnXqhKWlJUeOHDH8GHO7X3/9tUT7gdK//0F/nV9eXl6JjwG173NDCHFvkoQJIWqcZ599FoB3332XAwcOFFiXnJzM1KlT0el0jBgxothrmVasWMHGjRsNj/Py8pg9ezbp6ekMGTKkwPUpL774IgDPPfccYWFhBfaTlZVFSEiI4fHo0aNxd3dn9+7dhRKNzz//nMOHD1O/fv1SF7QwllGjRuHk5ERISEihL69vvfUWkZGRpdrftGnTcHFxYf369Xz66aeFJs7dv38/cXFxd91H48aNGTx4MKmpqTz77LPk5uYa1u3bt4+FCxei0WgICgoyLP/pp58KJFr51q9fj6IoBV4nTz31FG5ubrz//vt8++23hSbDzsvLY+PGjUXu7252795daALd1157jejoaNq1a1chX7C7dOlC3759iYuL48knnyQ9Pb3A+qioKE6cOGF4/PLLL6NWq5kyZUqRkz6npaXxww8/kJmZWao4vvjiiwLFNzIyMnjmmWdQFIUpU6ZgaWlZ4n3997//RafTMXLkSEJDQwutT0hI4LvvvjM8trGxYcKECWi1Wp555pkCsR8+fJgvv/yyVOdSmvc/6BO369evF/kDQXFq2+eGEKIEjFiZUQghyuyFF14wlFsPCAhQxo0bpwwePFixt7c3zClU1DxOd07W3Lt3b2XMmDGKj4+PYS6gS5cuFdrumWeeUQBFo9EoPXr0UMaOHav06dPnnpM1d+rUSRk7dqzi5+d3z0lXi5okVlGKLjefr7h5tO5Wor53796l2tftkzUHBAQoY8eOVdq0aaOYmZkpTz75pAIob7/9dpH7LMq2bdsME037+Pgoo0ePVh566KFST9ac/2/WsGFDZcyYMUq/fv0McX700UcF2ueXYm/SpIkyfPhwZezYscp9992nqFQqRa1WKytXrizQft++fYqLi4sCKN7e3soDDzygjBs3Trn//vsNE02vXr26ROebX4J9xowZikqlUrp06aKMHTvWMKGynZ1doRLw+SXq71b6v7h5wq5cuaK0aNFCARQnJydl6NChyqhRo4qdrHnhwoWG561NmzbKiBEjDJOFm5ubK4By8+bNEp3rnZM1BwYGKqNHj1Y8PDwUQGndurVhAuZ7ncftXnrpJcP7vWPHjsqoUaOURx55RPHz81M0Go1ib29foH1CQoLhOfD09DRMdG1iYqIEBQWVqkS9opTu/Z/f1sfHRxk/frzy+OOPK++//75hfUkma66Iz42SPK9CCOORJEwIUWOtX79eGTZsmOLh4aGYmJgodnZ2SpcuXZT33ntPSUtLK3Kb278ALV68WOnQoYNiYWGhODs7KxMmTFAuX75c7PHWrFmjBAYGKk5OToqZmZni5eWlDBkyRFm1alWhtuHh4crYsWMVd3d3xdTUVPH09FQee+yxIufnqu5JWH6Mffr0UaytrRU7Oztl4MCByoEDB5S33npLAZRvvvmmyH0W5+LFi8r06dOVRo0aKWZmZoqTk5PSqVMn5Y033igwv9XdYrpx44by/PPPK02aNFHMzMwUBwcHZeDAgcrGjRsLtd2xY4cSFBSkdOjQQXF2dlYsLCyUxo0bK2PGjFEOHTpUZIzXrl1TXnjhBaV169aKlZWVYmVlpTRp0kQZNmyYsmTJkkITIRfn9i/Df//9txIQEKBYWVkp9vb2yrBhw5STJ08W2qY8SZiiKEpKSoryxhtvKO3atVMsLS0VGxsbpWXLlkpwcHCBCY/zHTt2TJk0aZLSsGFDw3PZunVrZerUqcratWsVnU5XonPNf91ptVrlww8/VFq2bKmYm5srnp6eSlBQUKF58O51HrfbsWOHMmrUKKVevXqKqamp4uzsrLRr104JDg5WduzYUaj9jRs3lBkzZigeHh6Kubm50rJlS+XDDz9UdDpdqZMwRSn5+z8tLU0JDg5WvL29FRMTk0LvueKSMEWp2M8NScKEqN5UinLHWBAhhKjF+vTpw44dO4iMjCxVqWpRtEGDBrFx40b2799P165djR1OtTR58mSWLl3Ktm3b6NOnj7HDqVSNGjXi0qVLhYaZCiGEKEiuCRNCCHFXV69e5fr16wWW6XQ6PvnkEzZu3Ejz5s3p0qWLkaITQgghah4pUS+EEOKudu3axWOPPYafnx8NGzYkOzub8PBwoqKisLKyYtGiRZU6ka0QQghR20hPmBBCiLvq1KkTEydOJCkpiU2bNrFx40a0Wi0TJkzg0KFDUjZbCCGEKCW5JkwIIYQQQgghqpD0hAkhhBBCCCFEFZIkTAghhBBCCCGqkBTmKCedTkdMTAy2trZyYboQQgghhBB1mKIopKamUq9ePdTq4vu7JAkrp5iYGLy9vY0dhhBCCCGEEKKauHz5Ml5eXsWulySsnGxtbQH9E21nZ2fkaIQQQgghhBDGkpKSgre3tyFHKI4kYeWUPwTRzs5OkjAhhBBCCCHEPS9TksIcQgghhBBCCFGFJAkTQgghhBBCiCokSZgQQgghhBBCVCG5JqwKaLVacnNzjR2GEEZnamqKRqMxdhhCCCGEEEYlSVglUhSF2NhYkpKSjB2KENWGg4MDHh4eMq+eEEIIIeosScIqUX4C5ubmhpWVlXzpFHWaoihkZGQQFxcHgKenp5EjEkIIIYQwDknCKolWqzUkYM7OzsYOR4hqwdLSEoC4uDjc3NxkaKIQQggh6iQpzFFJ8q8Bs7KyMnIkQlQv+e8JuU5SCCGEEHWVJGGVTIYgClGQvCeEEEIIUddJEiaEEEIIIYQQVUiSMCHuMH/+fDp06GDsMEpt+/btqFQqqcYphBBCCFHNSRImihQbG8szzzxD48aNMTc3x9vbm4ceeogtW7YYO7S7UqlU/Pnnn8YOo9xUKpXhZm9vT/fu3dm6detdt+nWrRvXrl3D3t6+iqIUQgghhBBlIUmYKCQqKopOnTqxdetWPvjgA06cOMGGDRvo27cvQUFBZd6voijk5eUVWp6Tk1OecGutxYsXc+3aNfbs2YOLiwtDhgzh4sWLRbbNzc3FzMxM5t8SQgghhKgBJAkThTz99NOoVCoOHjzIyJEjad68Oa1bt+a5555j//79gD5RU6lUhIaGGrZLSkpCpVKxfft24N/hcevXr6dTp06Ym5uze/du+vTpQ3BwMLNmzcLFxYXAwEAAwsPDeeCBB7CxscHd3Z0JEyZw48YNw/779OnDzJkzeeGFF3BycsLDw4P58+cb1jdq1AiAhx9+GJVKZXhclCtXrjB27FicnJywtrbG39+fAwcOFNlWp9Pxxhtv4OXlhbm5OR06dGDDhg2G9Tk5OQQHB+Pp6YmFhQUNGzZkwYIFBZ6XadOm4erqip2dHffffz/Hjx+/579D/qTGbdq0YeHChWRmZhISEgLoe8oWLlzI0KFDsba25u233y5yOOKePXvo06cPVlZWODo6EhgYyM2bNw3ntWDBAnx8fLC0tKR9+/b8/vvv94xLCCGEEP/S6RS2nYnjalKmsUMRNYjME1aFFEUhM1drlGNbmmpK1EOSmJjIhg0bePvtt7G2ti603sHBodTHfvHFF/nwww9p3Lgxjo6OACxdupQZM2awZ88eQJ+o3H///UybNo1PPvmEzMxM5s6dy+jRowsMw1u6dCnPPfccBw4cYN++fUyePJnu3bszYMAADh06hJubG4sXL2bQoEHFzkGVlpZG7969qV+/Pn/99RceHh4cPXoUnU5XZPvPPvuMjz76iP/973/4+fnxww8/MHToUE6ePEmzZs34/PPP+euvv1i5ciUNGjTg8uXLXL582bD9qFGjsLS0ZP369djb2/O///2Pfv36cfbsWZycnEr0HObPr3V7r+H8+fN59913+fTTTzExMSnUSxYaGkq/fv2YOnUqn332GSYmJmzbtg2tVv8aXLBgAT///DPffPMNzZo1Y+fOnTz22GO4urrSu3fvEsUlhBBC1HWfbjnH51vOoVZBnxZujOvSgD4tXDHRSF+HKJ4kYVUoM1eL76sbjXLsU28EYmV273/u8+fPoygKLVu2rLBjv/HGGwwYMKDAsmbNmvH+++8bHr/11lv4+fnxzjvvGJb98MMPeHt7c/bsWZo3bw5Au3bteO211wz7+PLLL9myZQsDBgzA1dUV+LcHqTjLli0jPj6eQ4cOGZKgpk2bFtv+ww8/ZO7cuYwZMwaA9957j23btvHpp5/y1VdfER0dTbNmzejRowcqlYqGDRsatt29ezcHDx4kLi4Oc3Nzw/7+/PNPfv/9d5588sl7Pn8ZGRm88soraDSaAsnRuHHjmDJliuHxnUnY+++/j7+/P19//bVhWevWrQHIzs7mnXfeYfPmzQQEBADQuHFjdu/ezf/+9z9JwoQQQogSOHs9lYXbzwOgU2BrRBxbI+LwtLdgtL83j3b2pp6DpZGjFNWRJGGiAEVRKnyf/v7+hZZ16tSpwOPjx4+zbds2bGxsCrW9cOFCgSTsdp6ensTFxZUqntDQUPz8/ErUC5WSkkJMTAzdu3cvsLx79+6GIYWTJ09mwIABtGjRgkGDBjFkyBAGDhxoOK+0tDScnZ0LbJ+ZmcmFCxfueuyxY8ei0WjIzMzE1dWV77//vsD5F/W83nmeo0aNKnLd+fPnycjIKJQc5+Tk4Ofnd9f9CiGEEEI/DHHeqhPkahX6t3LjpQdb8euhy/x+5ArXkrP4bMs5vth6jr4t3BjXtQF9WrihUct120JPkrAqZGmq4dQbgUY7dkk0a9YMlUpFRETEXdup1fou9tuTttzc3CLbFjWs8c5laWlpPPTQQ7z33nuF2np6ehr+NjU1LbBOpVIVO4ywOPlD+ypKx44diYyMZP369WzevJnRo0fTv39/fv/9d9LS0vD09DRcJ3e7ew3t/OSTT+jfvz/29vaGXr7bFfW83u5u55mWlgbAunXrqF+/foF1+T12QgghhCjesoPRHLl0E2szDW8Ma0M9B0teerAVzw9szobwWJYfjGb/xUS2RMSx5Vbv2LwHWzG0fT1jhy6qAUnCqpBKpSrRkEBjcnJyIjAwkK+++oqZM2cW+qKflJSEg4ODISm4du2aoefk9iIdpdWxY0f++OMPGjVqhIlJ2Z8jU1NTwzVPxWnXrh2LFi0iMTHxnr1hdnZ21KtXjz179hQYordnzx66dOlSoN2jjz7Ko48+yiOPPMKgQYNITEykY8eOxMbGYmJictdCIUXx8PC46zDJe2nXrh1btmzh9ddfL7TO19cXc3NzoqOjZeihEEIIUUrXU7J4b73+B+s5gS0KDDk0N9EwrEN9hnWoz4X4NJYfiOb3o/resZL+KC5qP7liUBTy1VdfodVq6dKlC3/88Qfnzp3j9OnTfP7554brhywtLbnvvvt49913OX36NDt27OCVV14p8zGDgoJITExk7NixHDp0iAsXLrBx40amTJlyz6Tqdo0aNWLLli3ExsYaqgDeaezYsXh4eDB8+HD27NnDxYsX+eOPP9i3b1+R7efMmcN7773HihUrOHPmDC+++CKhoaE8++yzAHz88ccsX76ciIgIzp49y2+//YaHhwcODg7079+fgIAAhg8fzqZNm4iKimLv3r28/PLLHD58uPRPVCnMmzePQ4cO8fTTTxMWFkZERAQLFy7kxo0b2Nra8p///IfZs2ezdOlSLly4wNGjR/niiy9YunRppcYlhBBC1HTz/zpJanYe7b0dmBDQqNh2TVxteGWIL/vn9ePLcX70bVF4ZIuom6plErZgwQI6d+6Mra0tbm5uDB8+nDNnzhRo06dPnwIT2qpUKqZPn16gTXR0NIMHD8bKygo3NzfmzJlTaJ6q7du307FjR8zNzWnatClLliyp7NOr9ho3bszRo0fp27cvzz//PG3atGHAgAFs2bKFhQsXGtr98MMP5OXl0alTJ2bNmsVbb71V5mPm9zZptVoGDhxI27ZtmTVrFg4ODoahjyXx0UcfERISgre3d7HXNpmZmbFp0ybc3Nx48MEHadu2Le+++26x1RRnzpzJc889x/PPP0/btm3ZsGEDf/31F82aNQPA1tbWUASjc+fOREVF8c8//6BWq1GpVPzzzz/06tWLKVOm0Lx5c8aMGcOlS5dwd3cv/RNVCs2bN2fTpk0cP36cLl26EBAQwJo1aww9jW+++Sb//e9/WbBgAa1atWLQoEGsW7cOHx+fSo1LCCGEqMk2nYxlfXgsJmoV745oW6LrvCxMNQxpV08qJgoDlVIZlRjKadCgQYwZM4bOnTuTl5fHSy+9RHh4OKdOnTIMj+vTpw/NmzfnjTfeMGxnZWWFnZ0dAFqtlg4dOuDh4cEHH3zAtWvXmDhxIk888YShAl9kZCRt2rRh+vTpTJs2jS1btjBr1izWrVtnmLvqXlJSUrC3tyc5OdlwbICsrCwiIyPx8fHBwsKiop4aIWo8eW8IIYSoqVKzchnw8U5iU7KY0acJcwdVXDVpUTsUlxvcqVpeoHT7RLgAS5Yswc3NjSNHjtCrVy/Dcisrq2JLkW/atIlTp06xefNm3N3d6dChA2+++SZz585l/vz5mJmZ8c033+Dj48NHH30EQKtWrdi9ezeffPJJiZMwIYQQQghRN3y06SyxKVk0dLbi2X7NjB2OqMFqRJ9ocnIyQKEiCr/88gsuLi60adOGefPmkZGRYVi3b98+2rZtW2DIV2BgICkpKZw8edLQpn///gX2GRgYWOy1QaCfXyklJaXATQghhBBC1G7Hom+ydF8UAG8Pb4uFFNkQ5VAte8Jup9PpmDVrFt27d6dNmzaG5ePGjaNhw4bUq1ePsLAw5s6dy5kzZ1i1ahUAsbGxha65yX8cGxt71zYpKSlkZmYWWeJ7wYIFRVabE0IIIYQQtVOuVse8VSdQFBjRsT49mrkYOyRRw1X7JCwoKIjw8HB2795dYPmTTz5p+Ltt27Z4enrSr18/Lly4QJMmTSotnnnz5vHcc88ZHqekpODt7V1pxxNCCCGEEMb13a6LRMSm4mhlyiuDfY0djqgFqvVwxODgYNauXcu2bdvw8vK6a9uuXbsCcP78eUA/x9L169cLtMl/nH8dWXFt7Ozsip3o1tzcHDs7uwI3IYQQQghRO0XdSOezzecA+O8QX5yszYwckagNqmUSpigKwcHBrF69mq1bt5aoZHb+RMGenp4ABAQEcOLECeLi4gxtQkJCsLOzw9fX19Bmy5YtBfYTEhJimAtLCCGEEELUXVeTMpnz+3Gy83T0aOrCw371jR2SqCWq5XDEoKAgli1bxpo1a7C1tTVcw2Vvb4+lpSUXLlxg2bJlPPjggzg7OxMWFsbs2bPp1asX7dq1A2DgwIH4+voyYcIE3n//fWJjY3nllVcICgrC3NwcgOnTp/Pll1/ywgsvMHXqVLZu3crKlStZt26d0c5dCCGEEEIY1/HLSSzaHck/J66h1SmYm6h5++E2qFT3nhNMiJKolklY/oTAffr0KbB88eLFTJ48GTMzMzZv3synn35Keno63t7ejBw5kldeecXQVqPRsHbtWmbMmEFAQADW1tZMmjSpwLxiPj4+rFu3jtmzZ/PZZ5/h5eXFokWLpDy9EEIIIUQdo9UpbD59ne93RXIwKtGwvFsTZ54f2JyGztZGjE7UNtVysuaaRCZrFqJ05L0hhBCiOsnIyeP3I1f4YXckUQn66Y5M1CqGtq/H4z19aF3P3sgRipqkRk/WLER5REVF4ePjw7Fjx+jQoYPR4pg8eTJJSUn8+eefRouhLJYsWcKsWbNISkoydihCCCFEpVEUhaV7o/hk8zmSM3MBsLMwYfx9DZkU0AgPe/mhUFSealmYQxhXnz59mDVrVqHlS5YswcHBocrjKS1vb2+uXbtWYF65uigqKgqVSmW4OTs7M3DgQI4dO3bX7R599FHOnj1bRVEKIYQQVU+rU3jtr5PM//sUyZm5NHCy4vWhrdk3rx9zB7WUBExUOukJE7WORqMxTEMgYPPmzbRu3ZorV64wc+ZMHnjgASIiIopMqHNzc7G0tCx2igYhhBCipsvM0fLM8mNsPn0dlQrmPdCSx3s0RqOWohui6khPmCizyZMnM3z4cF5//XVcXV2xs7Nj+vTp5OTkGNrodDref/99mjZtirm5OQ0aNODtt982rD9x4gT3338/lpaWODs78+STT5KWllboGO+88w7u7u44ODjwxhtvkJeXx5w5c3BycsLLy4vFixcbtsnvAcqftmD79u2oVCq2bNmCv78/VlZWdOvWjTNnzhQ4n7feegs3NzdsbW2ZNm0aL7744j2HM548eZIhQ4ZgZ2eHra0tPXv25MKFC0W2zc7OZubMmbi5uWFhYUGPHj04dOiQYf3NmzcZP348rq6uWFpa0qxZswLndfnyZUaPHo2DgwNOTk4MGzaMqKiou8YH4OzsjIeHB/7+/nz44Ydcv36dAwcOGJ6nFStW0Lt3bywsLPjll1+K7PH8+++/6dy5MxYWFri4uPDwww8XOK///Oc/1K9fH2tra7p27cr27dvvGZcQQghR1W6kZTPmu/1sPn0dMxM1X43ryJO9mkgCJqqcJGFVSVEgJ904t0qqv7JlyxZOnz7N9u3bWb58OatWreL11183rJ83bx7vvvsu//3vfzl16hTLli3D3d0dgPT0dAIDA3F0dOTQoUP89ttvbN68meDg4ALH2Lp1KzExMezcuZOPP/6Y1157jSFDhuDo6MiBAweYPn06Tz31FFeuXLlrrC+//DIfffQRhw8fxsTEhKlTpxrW/fLLL7z99tu89957HDlyhAYNGhiqdBbn6tWr9OrVC3Nzc7Zu3cqRI0eYOnUqeXl5RbZ/4YUX+OOPP1i6dClHjx6ladOmBAYGkpior8CU/xytX7+e06dPs3DhQlxcXAB9D1VgYCC2trbs2rWLPXv2YGNjw6BBgwokvfeS38N1+zYvvvgizz77LKdPny6yMui6det4+OGHefDBBzl27BhbtmyhS5cuhvXBwcHs27ePX3/9lbCwMEaNGsWgQYM4d+5cieMSQgghKtvF+DRGfL2X45eTcLAyZdm0rjzY1tPYYYk6SoYjVqXcDHinnnGO/VIMmFV8aVUzMzN++OEHrKysaN26NW+88QZz5szhzTffJD09nc8++4wvv/ySSZMmAdCkSRN69OgBwLJly8jKyuLHH3/E2lof25dffslDDz3Ee++9Z0jWnJyc+Pzzz1Gr1bRo0YL333+fjIwMXnrpJeDfRG/37t2MGTOm2FjffvttevfuDegTj8GDB5OVlYWFhQVffPEFjz/+OFOmTAHg1VdfZdOmTQV65e701VdfYW9vz6+//oqpqSkAzZs3L7Jteno6CxcuZMmSJTzwwAMAfPfdd4SEhPD9998zZ84coqOj8fPzw9/fH4BGjRoZtl+xYgU6nY5FixYZ5ihZvHgxDg4ObN++nYEDBxYbZ76kpCTefPNNbGxs6NKlC5mZmQDMmjWLESNG3PV5GzNmTIHkun379gBER0ezePFioqOjqVdP/9r+z3/+w4YNG1i8eDHvvPPOPeMSQgghKtvhqESm/XiYpAz99V9LpnSmsauNscMSdZj0hIlyad++PVZWVobHAQEBpKWlcfnyZU6fPk12djb9+vUrctvTp0/Tvn17QwIG0L17d3Q6XYGhgq1bt0at/vel6u7uTtu2bQ2PNRoNzs7OxMXF3TXW/Im8ATw99b985W9z5syZAr07QKHHdwoNDaVnz56GBOxuLly4QG5uLt27dzcsMzU1pUuXLpw+fRqAGTNm8Ouvv9KhQwdeeOEF9u7da2h7/Phxzp8/j62tLTY2NtjY2ODk5ERWVlaxwx/zdevWDRsbGxwdHTl+/DgrVqwwJLiAIem723kW92944sQJtFotzZs3N8RlY2PDjh077hmXEEIIURXWn7jGuEUHSMrIpb2XPaue7iYJmDA66QmrSqZW+h4pYx27hOzs7EhOTi60PCkpCXv7ks+VUVHFHe5MclQqVZHLdDpdifeT35t0r23upqKLVzzwwANcunSJf/75h5CQEPr160dQUBAffvghaWlpdOrUiV9++aXQdq6urnfd74oVK/D19cXZ2bnIYhy3J8FFudt5pqWlodFoOHLkCBqNpsA6Gxv5D04IIYTxKIrCD3uieGvdKRQF+rdy5/OxHbAyk6+/wvikJ6wqqVT6IYHGuKlKfsFpixYtOHr0aKHlR48eLTTc7vjx44ZhbQD79+/HxsYGb29vmjVrhqWlJVu2bCnyOK1ateL48eOkp6cblu3Zs8cw7LAqtWjRokCRDKDQ4zu1a9eOXbt2kZube8/9N2nSBDMzM/bs2WNYlpuby6FDh/D19TUsc3V1ZdKkSfz88898+umnfPvttwB07NiRc+fO4ebmRtOmTQvc7pUYe3t706RJkzJPL9CuXbti/w39/PzQarXExcUViksqVAohhKhKiqIQeSOd5QejefbXY9y3YAtvrtUnYBMDGvK/CZ0kARPVhiRhopAZM2Zw9uxZZs6cSVhYGGfOnOHjjz9m+fLlPP/88wXa5uTk8Pjjj3Pq1Cn++ecfXnvtNYKDg1Gr1VhYWDB37lxeeOEFfvzxRy5cuMD+/fv5/vvvARg/fjwWFhZMmjSJ8PBwtm3bxjPPPMOECRMKDJerCs888wzff/89S5cu5dy5c7z11luEhYUZesyKEhwcTEpKCmPGjOHw4cOcO3eOn376qVDVRdD3Ns2YMYM5c+awYcMGTp06xRNPPEFGRgaPP/44oL8Obc2aNZw/f56TJ0+ydu1aWrVqBeifKxcXF4YNG8auXbuIjIxk+/btzJw5854FScrrtddeY/ny5bz22mucPn2aEydO8N577wH6a+DGjx/PxIkTWbVqFZGRkRw8eJAFCxawbt26So1LCCFE3VZU0tX3w+3MW3WCNaExXE/JxsxEzcsPtuL1oa2lAqKoVuTnAFFI48aN2blzJy+//DL9+/cnJyeHli1b8ttvvzFo0KACbfv160ezZs3o1asX2dnZjB07lvnz5xvW//e//8XExIRXX32VmJgYPD09mT59OgBWVlZs3LiRZ599ls6dO2NlZcXIkSP5+OOPq/J0AX2Sc/HiRf7zn/+QlZXF6NGjmTx5MgcPHix2G2dnZ7Zu3cqcOXPo3bs3Go2GDh06FLju63bvvvsuOp2OCRMmkJqair+/Pxs3bsTR0RHQFzmZN28eUVFRWFpa0rNnT3799VdA/1zt3LmTuXPnMmLECFJTU6lfvz79+vXDzs6u4p+Q2/Tp04fffvuNN998k3fffRc7Ozt69eplWL948WLeeustnn/+ea5evYqLiwv33XcfQ4YMqdS4hBBC1C2KohCVkMH+iwmG2/WU7AJtzDRqOjRw4L7GztzX2ImODRyxMNUUs0chjEelKJVUu7yOSElJwd7enuTk5AJfhrOysoiMjMTHxwcLi9o56/rkyZNJSkrizz//NHYolWLAgAF4eHjw008/GTuUWqUuvDeEEEKUnyRdoiYqLje4k/SECQFkZGTwzTffEBgYiEajYfny5WzevJmQkBBjhyaEEELUCZJ0ibpEkjAh0FdL/Oeff3j77bfJysqiRYsW/PHHH/Tv39/YoQkhhBC1kiRdoi6TJEyU2ZIlS4wdQoWxtLRk8+bNxg5DCCGEqPUib6Tz2eaz7JOkS9RhkoQJIYQQQogqM/+vk+w4Gw/oky4/Q9LljF8DB0m6RJ0gSVglk7onQhQk7wkhhKi7LidmsPOcPgH7fpI/3Zu6SNIl6iSZJ6ySmJqaAvqCD0KIf+W/J/LfI0IIIeqO5QejURTo2cyFfq3cJQETdZb0hFUSjUaDg4MDcXFxgH6ep7tN/CtEbacoChkZGcTFxeHg4IBGI//xCiFEXZKTp2Pl4csAjO/a0MjRCGFckoRVIg8PDwBDIiaEAAcHB8N7QwghRN2x6VQsN9JycLczp18rN2OHI4RRSRJWiVQqFZ6enri5uZGbm2vscIQwOlNTU+kBE0KIOuqX/dEAPOrvjalGrogRdZskYVVAo9HIF08hhBBC1FkX4tPYdzEBtQoe7dLA2OEIYXTyM4QQQgghRBncSMvmfFyqscOoEZYf0PeC3d/SjfoOlkaORgjjkyRMCCGEEKKU4lKzGPL5bgI/3cXhqERjh1OtZeVq+f3oFUAKcgiRT5IwIYSoZo5cSmTBP6dJysgxdihCiCLkanUELztGbEoWWp3CK3+Gk6vVGTusMsvT6gi7ksSiXRd5d30EJ2OSK3T//5y4RlJGLvUdLOnV3LVC911r6HSQcAHOhRg7ElFF5JowIYSoRhRF4fmVx4lKyGDfxQR+ntYVOwuZU02I6uT9DREcjEzExtwEU42KiNhUFu+J5MleTYwdWolk5WoJvZzEochEDkYlcvTSTdJztIb13+y4QEBjZ6b19KFvCzfU6vJNsfPLraGIY7t4oynnvmqttFj4oiOoNPDSVTCVIZu1nSRhQghRjRyKuklUgn5C67AryUxZfIgfp3bB2lw+roWoDtaFXeO7XZEAfDiqHalZecz5PYxPQs4xuF29anm9U3JmLkcuJXIw8iaHohI5cSWZnDt67mwtTPBv6IilmYaNJ6+z72IC+y4m0NjVmsd7+DDCzwtLs9IXGYuITeHIpZuYqFWM9veuqFOqfWw9wcoZMhIg7jTU72jsiEQlk//VhRCiGsmfyDSgsTMnY5I5cukmjy89xOLJXcr0BUgIUXHOx6Uy5/fjADzVuzGD2niiKAq/HbnCwchE5v91ku8m+hs5SohLyeJgVOKtnq6bRMSmoCgF27jZmtPZx4kujZzo3MiJFh62hl6qmKRMlu6NYtnBaC7Gp/Py6nA+3HiGCfc15LGAhrjZWpQ4lmW3esEGtnbHza7k29U5KhV4tIWL2yH2hCRhdYAkYUIIUU2kZeexLuwaAM8PbI6pRs34RQfYfzGRJ386zHcT/bEwlURMCGNIzcrlyZ+OkJGjJaCxM3MGtgD0c4K+NbwND362i5BT19l0MpaBratuQnpFUYhKyDAMLTwUlcilW73pt2vkbEXnRk6GxKuhsxUqVdFDA+s5WDLvwVY8068ZKw9d5oc9kVy5mcnnW8/zzY6LPNrZm5cHt7rn51F6dh6rjl4FpCBHidyehIlaT5IwIYSoJtaFxZCZq6WxizWdGjqiUqlYMqUzE384yK5zNwhedpSvx3fCzERqKglRlRRF4YXfw7gYn46HnQVfjPPD5LbJhpu72/JEr8Ys3H6B1/8+RY9mLliZVc5XLK1OISI2hUORiRyKusnBqETiU7MLtFGpoJWHHV189L1cnRs5lqkXysbchKk9fJjUrRGbTsayaHckRy7d5Kf9l4iITeHbCf44WpsVu/3fx2NIy87Dx8WagMbOpT5+nePRTn8vSVidIEmYEEJUE78d1pdwHuXvbfiF2r+RE4sm+TNl8SE2n47j2V+P8cXYgl8AhRCV67tdF1kfHoupRsXXj3XExca8UJuZ9zfj7+MxXLmZyWdbzjHvgVYVcuzsPC1hV5I5GKnv5ToSdZPU7LwCbcw0atp72xt6ujo1dKzQgj4atYoH2nryQFtPtp+J45nlxzgUdZORC/eyeEpnGjpbF7ndsoP/FuQob3GPOsGjrf7+eri+WqJaPudrM5Wi3DlKWJRGSkoK9vb2JCcnY2dnZ+xwhBA11IX4NPp9tAONWsW+F+8v9Kv19jNxPPnjEXK0OoZ1qMfHoztIlTEhqsDeCzd4bNEBdAq8ObwNE+4rfljdltPXeXzpYUzUKtbO7EFLj9J/L0jNyuVodBIHIxM4FHmT0CtJ5OQVLKJhY25Cx4aOdGnkSOdGTrT3dqjSocpnr6cyZfEhriZl4mxtxqJJ/vg1cCzQJuxKEkO/3IOZRs3+l/rhdJceM3GLNg/eqQfabHjmKDjXjGqboqCS5gbSEyaEENVAfi9Yn+auRQ4b6tPCja/Gd2TGz0dYExqDuYmad0e0k1+XhahE15IzeWbZMXQKjOhYn8e6Nrhr+36t3Als7c7Gk9d5ZXU4K58KuOd7NDtPy7aIeA5EJnAoKpFTMSno7vh53MXG7NawQie6+DjR0sPWqL3hzd1tWf10N6YuPUT41RTGfrefz8b4EXjbtXD5BTkebOshCVhJaUzA3RdijumHJEoSVqtJEiaEEEaWp9Xxx9H8oYhexbYb4OvOZ2P8eGb5UVYevkJ6tpaRnerTxccZGylhL0SFSs7I5elfjpKQnkMrTzveHt622EIWt3vtodbsOneDw5du8tuRyzzauejELT07j2UHolm0+yLXUwpe0+XtZEnnRk50vXVNl4+LdYmOXZXc7CxY8WQAwcuOsu1MPNN/PsJ/B/sytYcPKVm5rAmNAWD8XXoORRE82v6bhLUebuxoRCWS/7WFEMLIdpyNJz41GydrM+5v6X7XtoPbeZKjbc9zK4+z7sQ11p24hkator2XPd2butCtiQsdGzpgbiJVFIW4m4ycPKJuZHDlZgZXbmbeumUY7lOy9Ndd2VmY8M1jHUs8RUQ9B0tm92/O2/+cZsH6CAb4FuwJupmew+K9USzdG0VyZi4A7nbmDPT1MFQu9LCvGaXcrc1N+G6iP6/+dZJlB6J5Y+0pLt/MoKGTFZm5Wpq72+Df0PHeOxL/kuIcdUa1TMIWLFjAqlWriIiIwNLSkm7duvHee+/RokWLQm0VReHBBx9kw4YNrF69muHDhxvWRUdHM2PGDLZt24aNjQ2TJk1iwYIFmJj8e9rbt2/nueee4+TJk3h7e/PKK68wefLkKjhLIYTQy58b7GG/+iWqfPiwnxcedpb8dfwqe84nEJ2YwdHoJI5GJ/HF1vNYmKrp3MiJgCbOdG/iQpv69nL9mBC32X3uBjN+PlKowMWd6jtY8t7IdsUWnijO5O6N+OPoFSJiU1nwz2k+GNWea8mZLNoVybID0WTmagHwcbFmeu/GDPerX2N/ODHRqHl7eBsaOFnx7voIFu+JMnzejOvSoNr14FV7+cU5JAmr9aplErZjxw6CgoLo3LkzeXl5vPTSSwwcOJBTp05hbV3wg/DTTz8t8g2u1WoZPHgwHh4e7N27l2vXrjFx4kRMTU155513AIiMjGTw4MFMnz6dX375hS1btjBt2jQ8PT0JDAysknMVQtRtN9Ky2XI6DoDR/t4l3i6giTMBTfQlny8nZrDvQgJ7Ltxg74UE4lOz2XXuBrvO3QDOYGthwn2NnenexJnuTV1o6mYjX4xEnXU0+iZP/nSYjBwt9pamNHCywtvJEi9HK7wcLW/d9H+Xtcy8qUbN2w+3ZeTCvfx25App2XlsPn2dXK3+Yi9fTzuC+jZlUBuPWvEDiUqlYnrvJtRzsOQ/K4+To9VhYarm4Y7FD68WxXBvrb9PjYH0G2DtYtx4RKWpEdUR4+PjcXNzY8eOHfTq1cuwPDQ0lCFDhnD48GE8PT0L9IStX7+eIUOGEBMTg7u7fnjPN998w9y5c4mPj8fMzIy5c+eybt06wsPDDfscM2YMSUlJbNiwoUSxSXVEIUR5LNp1kbfWnaa9lz1rgnuUe3+KonA+Lo0952+w50IC+y8mkJpV8Nd+V1tzut3qJevW1BkvR6tyH1eImiAiNoVH/7ef5MxcejZzYdEk/0rtgZq3KozlBy8bHnfxceLpPk3o3dy11v4QcjAykXmrwhjR0Yugvk2NHU7N9LkfJF6ECX9Ck77GjkaUUq2qjpicnAyAk5OTYVlGRgbjxo3jq6++wsOj8Mz0+/bto23btoYEDCAwMJAZM2Zw8uRJ/Pz82LdvH/379y+wXWBgILNmzSo2luzsbLKz/72ANiUlpaynJYSo4xRFYcUh/Re0UaXoBbsblUpFM3dbmrnbMrm7D3laHSdjUvS9ZOf11dfiU7NZExpjuHC+obMV3Zq40K2JM92aOONcxBxIxqYoCjvOxuNma4FvPfnBS5TepYR0Jnx/kOTMXDo2cOB/EzpV+hDAuYNaEp2YgZWZCU/1aox/I6d7b1TDdfFxYsvzfYwdRs3m0VafhMWekCSsFqv2SZhOp2PWrFl0796dNm3aGJbPnj2bbt26MWzYsCK3i42NLZCAAYbHsbGxd22TkpJCZmYmlpaWhfa7YMECXn/99XKdkxBCABy/ksy5uDTMTdQ81L5epRzDRKOmvbcD7b0deLpPU7JytRyLTmLvhRvsOX+D41eSuZSQwaWEaJbfmli1pYftrSIfznTxccK2Aid9LQudTuHtf07z/e5IzDRqFj7WkX6t7l7ARIjbXU/J4rHvDxCfmk1LD1sWT+5S5qGGpeFgZcYv0+6r9OOIWsajLZxaI9eF1XLVPgkLCgoiPDyc3bt3G5b99ddfbN26lWPHjlV5PPPmzeO5554zPE5JScHbu2J+wRZC1C35BTkeaOOBvWXVJDoWphrD9WTPD2xBWnYeByMT2HM+gT3nbxARm2q4fb87Eo1axQNtPPh4dIcSFQ2paDl5Oub8ftzQa5ej1TH95yMsHN+J/r6SiIl7S8rIYcL3B7icmElDZyt+nNoFeyvj/rAgxF1JhcQ6oVonYcHBwaxdu5adO3fi5fXvxZ1bt27lwoULODg4FGg/cuRIevbsyfbt2/Hw8ODgwYMF1l+/fh3AMHzRw8PDsOz2NnZ2dkX2ggGYm5tjbl79huoIIWqWzBwtf99KLEpTkKOi2ZibcH9Ld0Np/IS0bPZd1Cdley/c4FJCBmvDrtGrmSujO1dtnOnZeUz/+Qi7zt3ARK3i3ZHt2BYRx7oT15jxyxG+Ht+JAZKIibtIz85j8uJDnL2ehrudOT8/3rXIydCFqFbyKyTeOAu5mWBa9HdSUbMZb7r1u1AUheDgYFavXs3WrVvx8fEpsP7FF18kLCyM0NBQww3gk08+YfHixQAEBARw4sQJ4uLiDNuFhIRgZ2eHr6+voc2WLVsK7DskJISAgIBKPDshhIANJ6+Rmp2Hl6Ml9zV2NnY4Bs425gxpV48FI9qyY05fXnygJQDf7LyAVld1dZwS0rIZ991+dp27gZWZhu8nd+aRTl58NqYDg9t5kqtVePqXI2w6GVtlMYmaJTtPy5M/HSb0chIOVqb89HhXvJ2kCI2oAWw9wcoZFC3EnTZ2NKKSVMskLCgoiJ9//plly5Zha2tLbGwssbGxZGZmAvoerDZt2hS4ATRo0MCQsA0cOBBfX18mTJjA8ePH2bhxI6+88gpBQUGGnqzp06dz8eJFXnjhBSIiIvj6669ZuXIls2fPNs6JCyHqjN8OXwFgVCdv1NW4RPVj9zXEzsKEi/HphJyqmoTncmIGo77Zx/EryThambLsifvo3dwV0F/j9tmjHXiofT1ytQpBy46yURIxcYc8rY6Zy4+x53wC1mYalkzpQnN3W2OHJUTJqFQyX1gdUC2TsIULF5KcnEyfPn3w9PQ03FasWFHifWg0GtauXYtGoyEgIIDHHnuMiRMn8sYbbxja+Pj4sG7dOkJCQmjfvj0fffQRixYtkjnChBCV6nJiBnsvJKBSwchO9Y0dzl3ZmJswMaARAAt3XKSyZzU5fS2FkQv3cvFGOvUdLPl9Rjc6eDsUaGOiUfPJ6PYMzU/EfjnKhnBJxISeTqfw4qoTbDx5HTONmu8m+hd6DQlR7UkSVutVy2vCyvKffFHbNGzYkH/++eeu2/Xp08coBT6EEHXXb0f0vWA9mrrUiDm6JndvxHe7LnL8chL7LibQrUnlTB564GIC0348TGpWHi3cbVk6tQse9kVfv2OiUfPx6PaoVLAmNIbgZUf5cpwfg9p4VkpsomZQFH0lzd+PXEGjVvHFOD+6NZXJbkUNJMU5ar1q2RMmhBC1lVan8PutqoiPdPK6R+vqwcXG3FA85JsdFyvlGCGnrjPhh4OkZuXh39CRlU8FFJuA5TPRqPloVHuGd6hHnk4haNkx1p+4VinxiZrhy63n+X53JADvjWxHYOvC84gKUSPk94RdDwedzrixiEohSZgQQlShvRduEJOchZ2FSY36gvhkr8Zo1Cp2no0n/Gpyhe77VEwKwcuOkpOno38rd36e1rXEJcRNNGo+Gt2Bh/3qo9UpBC8/xrowScTqoh/3RfFRyFkAXh3iW2N+5BCiSM7NQGMOOWlwM9LY0YhKIEmYEEJUoS2n9RVbB7fzxMJUY+RoSs7byYoh7fRD/b7ZcaHC9pucmcuMX46Qnaejd3NXvnmsY6mfF41axYej2jPiViI289djrA2LqbAYRfX357GrvLrmJADP9mvG1B4+99hCiGpOYwLu+mreMiSxdpIkTAghqtCe8zcA6NXM1ciRlN5TvZoA8M+Ja1xKSC/3/nQ6hedXhnIpIYP6DpZ8+mgHTDRl+29Jo1bxwaj2jOzohVan8Oyvofx9XBKxumDzqes8/9txACZ3a8Ss/s2MHJEQFUSKc9RqkoQJIUQViUvJ4lxcGioVBDSpPnODlZRvPTv6tHBFp8C3O8t/bdjCHRfYfDoOMxM13zzWCUdrs3LtT6NW8f4j7Xikkz4Rm7UilL8kEavV9l9MIGjZUbQ6hRF+9Xl1iC8qVfWd8kGIUpHiHLWaJGFCCFFF9l5IAKB1PTscrMqXcBjL9N763rDfjlwhPjW7zPvZc/4GH206A8AbQ1vT1su+QuLTqFW8N7Ido/ITsV+PsSb0aoXsW1QvJ64kM23pYbJvXUv43iPtqvWce0KUmvSE1WqShAkhRBXZfWsoYvcaXDK7q48Tfg0cyMnTsXhP2S4Wj0nK5Jnlx9ApMNrfizFdGlRojPmJ2Gh/L3QKzF4RKolYLXM+Lo1Jiw+Slp3HfY2d+HKcH6ZlHMoqRLXl3lp/nxoD6TeMG4uocPKJJYQQVUBRFPbmJ2GVNM9WVVCpVIbesJ/2XyI1K7dU22fnaXn6l6MkpufQup4dbwxrUxlholareHdEO8Z09jYkYquPXamUY4mqdeVmBhO+P0Bieg7tvOxZNKlzjSpyI0SJmduCU2P939IbVutIEiaEEFUgKiGDmOQszDRqOjdyMnY45TKglTtNXK1Jzcpj2YHoUm371trThF5Ows7ChIXjO1Xql2e1WsU7D7dlbBd9Ivb8yuOsOiqJWE12Iy2bCd8f5FpyFk3dbFgypQs25ibGDkuIyiNDEmstScKEEKIK5FdF9GvggKVZzf7VXq1W8dSt3rDvd0eSnact0Xarj13hp/2XAPh0TAcaOFtVWoz51GoVbw9vy9guDfSJ2G/H+eOIJGI1UXJmLhO/P0jkjXTqO1jy0+NdcCpnMRchqj1JwmotScKEEKIK7L1Q868Hu93wDvXxsLMgLjWb1Ufvfb3V6WspzFul/xIx8/6m3N/SvbJDNNAnYm0Y17UBigL/+f04v0siVqNk5miZtvQQp66l4GJjzs/TuuJpb2nssISofFIhsdaSJEwIISqZTqcYKiPWliTMzETNtJ76CXH/t/MiWp1SqI1Op3AtOZMDFxOY8fMRsnJ19GzmwrP9m1d1uKjVKt4a1obH7tMnYnN+P85vhy9XeRx1naIUfp3cS06ejhm/HOFQ1E1sLUz4cWoXfFysKyE6Iaqh/J6wG2chN9O4sYgKJQOphRCikp26lkJSRi425ia0r6BS7NXB2C4N+GLreSJvpPPp5rPYmJtw+WYG0YmZXEnM4MrNTHK0OkP7+g6WfD7GD42Ryoir1SrevFUI5Of90bzwRxiKAqM7exslnromM0fLw1/vITNXy38GtmBIO897zuml1Sk8tzKU7WfisTBVs3hyZ3zr2VVRxEJUA7aeYOUMGQkQdxrqdzR2RKKCSBImhBCVLP96sK4+TpjUojLa1uYmTApoyOdbz/PF1vNFttGoVdR3sKSpmw1zB7Us94TM5aVS6RMxtUrFj/suMXdVGAoKj3au2DL5orC1YTFExKYC8MzyY/y4L4rXHmpNm/pF/zChKAqvrglnbdg1TDUqvnmsE/41vKiNEKWmUul7wy5u1w9JlCSs1pAkTAghKtmeW0MRu9WSoYi3m9rDhyPRN8nI0dLAyQpvRyu8nSzxvvW3p71FtUs8VSoVrw9tjQpYuu8Sc/84gaJQ4fOViYKWHdRX0uzi40TYlSQORd3koS93M6qTF/8JbIGbrUWB9h9sPMMvB6JRqeCTRzvQp4WbMcIWwvhuT8JErSFJmBBCVKLsPC0HI/VJWI9amIQ5WJnxy7T7jB1GqalUKuYPbY1KpWLJ3iheXHUCBf0QS1HxTsWkcCw6CRO1ii/H+aHVKby3PoI/Q2NYefgK/5yIJfj+pkzp3ghzEw3/23GBr7dfAOCdh9sypF09I5+BEEYkxTlqJUnChBCiEh2LTiIrV4eLjTnN3W2MHY64jUql4rWHfFGpYPGeKOat0veIjesqiVhFW3ZQPzVBYGsPQ4/Xp2P8mBDQiDf+PsnxK8m8uz6C5QejGdDKnUW7IwF48YGWkhgLkV+c43o46HSgrl6jC0TZyL+iEEJUor23rgfr1sT5nkUIRNVTqVS8OsSXqd31lR5fWn2Cn2/NZSYqRnp2Hn8eiwEKJ7idGjqy+unufDSqPW625lxKyDAkYNN7N2H6rfnohKjTnJuBxhxy0iApytjRiAoiSZgQQlSiPYbS9M5GjkQUR6VS8d8hrXi8hz4Re+XPcEnEKtDfx2NIy86jkbMVAY0Lvw/UahUjO3mx7T99COrbBFsLE6Z292HuoBZGiFaIakhjAu6++r9lSGKtIUmYEEJUktSsXEIvJwHQrUntux6sNlGpVLwyuBVP3Jr77NU14UTEphg5qtrhlwP6ghzjujZAfZfpCazNTZgT2JKw1wby6kO+0nMsxO3yhyRKElZrSBImhBCV5GBkIlqdQkNnK7ydrIwdjrgHlUrFSw+2IrC1OzoFXv/rVJkmFxb/OnElmRNXkzHTqHmkU8nmY5PkS4giSHGOWkeSMCGEqCR7zt8qTS+9YDWGvkfMFzMTNfsuJrDxZKyxQ6rR8gtyDGrjgZOR54gTokaTnrBaR5IwIYSoJHsv6ItyyPVgNYu3kxVP9WoMwFvrTpOVqzVyRDVTalYua0KLLsghhCgl99b6+5SrkJ5g3FhEhZAkTAghKkF8ajYRsakARRYjENXbjD5N8LCz4MrNTBbtumjscGqkP0NjyMjR0sTVmq4+TsYOR4iazdwWnPQ/DnFdesNqA0nChBCiEuT3gvl62uFsY27kaERpWZmZMO/BlgB8te0C15IzjRxRzaIoCssMBTkaynVeQlQEGZJYq0gSJoQQd5Gr1XEyJpkVh6J55c8TvLT6BClZuffcbu95KU1f0w1tXw//ho5k5mp5d32EscOpUUIvJ3H6WgpmJmpGdqxv7HCEqB0kCatVTIwdgBBCVBe5Wh1nYlMJv6qv6BZ+NZnTsank5OkKtIu4lsKPj3fFxrz4j9A9t3rCujWVohw1lUql4rWHWjP0q92sCY1hwn0N8W8kw+pKIr8s/ZB2njhYSUEOISqEe34SFm7cOESFkCRMCFEn5eTpOHv9joTrWio5Wl2htrYWJrStb08rTzt+P3KFo9FJTF1yiCVTOmNlVvhjNDohgys3MzFRq+giX9prtLZe9ozu5M2Kw5d5/e9TrAnqfte5rmoSRVFIzszlRlo2iem5tPS0xc7CtNz7Tc7MZW2YviDHeCnIIUTFcWulv79xFrS5oCn/+1UYjyRhQohaLz/hOnFbwhVRTMJlZ2FCWy972tS3p+2tWwMnK8M1LcM61GP8dwc4GJnItKWH+WFyZyxMNQX2sfu8vhfMr4ED1nfpLRM1w5xBLfjnxDVOXE3mtyOXebRz9U0sFEUhJSuPG2nZxKdmF3GfY/g7IS2nwHvAydqMH6d2oU19+3LFsProFbJydbRwt6VjA8fynpIQIp+9N5jZQE4aJFwAt5bGjkiUg3w7EELUKvkJV9iVfxOuM7ElS7ja1XfA28nyrkUE2nk5sGRqFyZ+f4C9FxJ48qcjfDuhU4FEbI+hNL0MRawNXGzMebZ/M95ad5oPNp7hgbaeFdJjVFKKopCWnWdIou5Mrm5PsOLTsgsNn70XOwsTNGoViek5jP12Pz9M6UznMvbgKopiGIo4rmsDKcghREVSq8G1JVw9DHGnJAmr4SQJE0LUeAcjE1l97OpdEy57S1Pa1i/Yw3WvhKs4nRo6snhKFyb9cJCdZ+MJ+uUoCx/rhJmJGp1OYd+F/KIckoTVFhMDGrHsYDQX49P5Yss5Xh7sW+nHTEjLZsqSQ5yJTSW7lImVrbkJrrbmuNiY42JrhquN/u/8Za625rjYmuNsbYaFqYbUrFweX3qYg5GJTPj+AP+b4E/v5q6ljvnwpZuci0vD0lTDw1KQQ4iK59bqVhJ22tiRiHKSJEwIUaOlZecxdckh0rLzDMscrAonXF6OZUu4itPFx4nvJ/kzZckhtkTE8czyo3w5riPnrqeRmJ6DlZmG9l4OFXY8YVxmJmr+O8SXKYsPsXhPFGO6NKCJq02lHvP3I1cIu5JseGxtpimYRN1272JjVmDZnUNk78XWwpSlU7ow45cjbD8Tz7Slh/h8jB8PtPUs1X7yy9I/1L5qewuFqDPcbv0AFHfKuHGIcpMkTAhRo/0VGkNadh7eTpbMe6BVpSRcxenW1IVvJ/rzxNLDbDx5ndkrQg3X03TxccLMRGYBqU36tnDj/pZubI2I4621p1g8pUulHu/PUH1xi5cfbMX4+xoUWQSmIlmaafh2gj+zV4ayLuwaQcuO8t7Idozy9y7R9jfTc1h34hqgnxtMCFEJ8otzSE9YjSffEIQQNZb++pNLAEwKaMSDbT3xvq2IRlXo3dyVhY91xFSjYm3YNT7edBaAHjIUsVb67xBfTDUqtp2JZ1tEXKUd5+z1VE5fS8FUo+KRTl6VnoDlMzNR8/kYP8Z09kanwJzfw1i8J/Ke2yVn5PL19vPk5Onw9bSjvVf5insIIYrh3lp/n3gRcmUS+ZqsWiZhCxYsoHPnztja2uLm5sbw4cM5c+ZMgTZPPfUUTZo0wdLSEldXV4YNG0ZERMHJNKOjoxk8eDBWVla4ubkxZ84c8vLyCrTZvn07HTt2xNzcnKZNm7JkyZLKPj0hRAUJu5LMyZj8CWG9jBZHv1bufDG2Ixq1ynA9WrcmkoTVRj4u1kzt7gPANzsuVNpx/rrVC9a7uSuO1lU7z5ZGrWLBiLZM66E/z9f/PsXnW86hKIqhTZ5Wx5FLiXwccpaHv96D35ub+G6XPlkbf58U5BCi0li7gpUzoED8mXs2F9VXtUzCduzYQVBQEPv37yckJITc3FwGDhxIenq6oU2nTp1YvHgxp0+fZuPGjSiKwsCBA9FqtQBotVoGDx5MTk4Oe/fuZenSpSxZsoRXX33VsI/IyEgGDx5M3759CQ0NZdasWUybNo2NGzdW+TkLIUov//qTwW09q/yL6p0GtfHgszEdUKvAy9GSlh62Ro1HVJ7xt4baHbl0s8C1iBVFURTWHL8KwLAOxiluoVKpeHlwK2b3bw7AxyFneXPtaZYdiGb6T0fwezOEkQv38fmWcxyLTkKnQDM3G2b3b86YalzCX4gaT6W67bowGZJYk6mU23/aqqbi4+Nxc3Njx44d9OrVq8g2YWFhtG/fnvPnz9OkSRPWr1/PkCFDiImJwd3dHYBvvvmGuXPnEh8fj5mZGXPnzmXdunWEh/878/iYMWNISkpiw4YNJYotJSUFe3t7kpOTsbOzK//JClGNaHUKSRk5JKbnkJCew81b94m3bgAjO3rR1ghDj1Kycun69hYyc7X8Nj2gzCW1K9rF+DSszU1wt7MwdiiiEvX+YBuXEjJYNNGf/r7uFbrvI5duMnLhXqzMNBx5ZQCWZqUrslHRftgdyRtrCxcBsLc0pUczF3o1c6FnM1fqOVgaIToh6qB/5sDBb6HbTBj4prGjEXcoaW5QIwpzJCfrq0M5ORX9JSs9PZ3Fixfj4+ODt7f+AuJ9+/bRtm1bQwIGEBgYyIwZMzh58iR+fn7s27eP/v37F9hXYGAgs2bNqpwTEcLIsnK1hgQq/1YwucousC4pM5d7/UyzZG8U3Zs682SvJvRq5lJlw5D+PHaVzFwtzdxs8G9YfSaEbVzJFfNE9dCzmQuXEqLZdS6+wpOwv0L1vWCBrT2MnoABTO3hg62FCW//c5qmrjb0bOZKr+YutPNyQKOWYYdCVDkpzlErVPskTKfTMWvWLLp3706bNm0KrPv666954YUXSE9Pp0WLFoSEhGBmph+SFBsbWyABAwyPY2Nj79omJSWFzMxMLC0L/6qXnZ1Ndna24XFKSkr5T1KIUsjV6kjNyiM1K/fW/b9/p2Xr/07OzDUkV4m39V5l5GjLdEwHK1OcrMxwsi54u5qUydqwa+w5n8Ce8wm09LDlqd6NGdKuHqaayhvtrCiKYSiiTAgrjKFnM1d+3h/NznM3KnS/eVoda8P0FQaHdqhXofsuj1H+3iWukiiEqGQyHLFWqPZJWFBQEOHh4ezevbvQuvHjxzNgwACuXbvGhx9+yOjRo9mzZw8WFpU3DGjBggW8/vrrlbZ/Ie5m48lYnll2rMjJiEvKVKPC8Y6EytnaDCdrc5ysTW/d/7vO0coUk7skVHMCW/DD7ih+PRRNRGwqs1cc54MNZ5jaw4cxXRpgY17xHzNHo5OIiE3FwlTNCD/jFeQQdVe3Js5o1Coib6RzOTEDbyerCtnvngsJJKTn4GxtJhU2hRBFc22pv0+5AlnJYCHVSGuiap2EBQcHs3btWnbu3ImXV+EvWvb29tjb29OsWTPuu+8+HB0dWb16NWPHjsXDw4ODBw8WaH/9+nUAPDw8DPf5y25vY2dnV2QvGMC8efN47rnnDI9TUlIMQyCFqEw6ncKHG88YEjArMw22FibYWphiY26CrYUJdrf+trM0wcnaHGdrMxxvT7RszLA1N6nQniMvRytefciXZ/s14+cDl1i8J5KY5CzeWneaz7eco29LN8xN1GjUakw1KjRqFaYatf5ercLcVMNwv/rUL8X1JPll6Ye0q4e9lUwIK6qerYUpHRs4cCjqJrvO3WBc14opRrHmmH4o4uB2npXamyyEqMEsHcCuPqRchbgIaNDV2BGJMqiWSZiiKDzzzDOsXr2a7du34+PjU6JtFEUxDBUMCAjg7bffJi4uDjc3NwBCQkKws7PD19fX0Oaff/4psJ+QkBACAgKKPY65uTnm5uZlPTUhymz72TjOxaVhY27Cnrn3V7vkw97KlKC+TXm8hw+rj13lu50XuXgjnTW3Sm3fzY/7olg3sycuNvd+byVn5LIuLH9CWKnCJoynZzPXW0lYfIW8FjNztGw8qR8uP6waDUUUQlRDbq1uJWGnJAmroaplEhYUFMSyZctYs2YNtra2hmu47O3tsbS05OLFi6xYsYKBAwfi6urKlStXePfdd7G0tOTBBx8EYODAgfj6+jJhwgTef/99YmNjeeWVVwgKCjIkUdOnT+fLL7/khRdeYOrUqWzdupWVK1eybt06o527EMX5346LgD7xqG4J2O0sTDWM7dKAR/292X42jvNxaeRqFbQ6hTytjjydor9pFfJ0OnacjedSQgazV4SydEoX1Pe40P+Po1fIztPR0sMWP2+HqjkpIYrQs5kLH4ecZff5G+RpdXcdtlsSWyKuk56jxcvRko4Nqk+xGSFENeTWCs5vluvCarBqmYQtXLgQgD59+hRYvnjxYiZPnoyFhQW7du3i008/5ebNm7i7u9OrVy/27t1r6PXSaDSsXbuWGTNmEBAQgLW1NZMmTeKNN94w7M/Hx4d169Yxe/ZsPvvsM7y8vFi0aBGBgYFVdq6icimKQlaurlpUGCuP45eTOBCZiIlaxZTujYwdTomo1Srub+nO/S3vXjnu7PVUhn65m13nbvDVtvM8069ZsW0VRTEMRRx/X0MpyCGMqp2XA/aWpiRn5nL8SjKdylml889j+l7jYR3qyWtbCHF3huIchaePEDVDtUzC7jV1Wb169QoNIyxKw4YN79muT58+HDt2rFTxiZohT6tj9srjrA2L4WG/+jw/sEWprjuqTr7dqe8FG9qhHp72NfMcitPc3ZY3h7Vhzu9hfLL5LJ0aOdKtSdEFCQ5GJnIhPh0rMw3DZbiWMDKNWkWPpi6sO3GNXefiy5WEJWXksONsHGC8CZqFEDWIlKmv8eSqX1Er6XQKL646wd/HY1AUWHX0Kn0/3M47/5wmOSPX2OGVSnRCBuvD9ddAPdmrsZGjqRyj/L15pJMXOgWe/TWU+NTsItstO6gvSz+0fT1sLarvkExRd/Rspv/BYFc5S9WvD48lV6vQ0sOW5u62FRGaEKI2c2kBqCDjBqTFGTsaUQaShIlaR1EU3lp3mt+PXEGjVvHyg624r7ETOXk6vt15kZ7vb+V/Oy6QlVu2ObOq2qLdF9Ep0Lu5Ky09ip95vaZ7c1gbmrvbEJ+azawVx9DqCvaIJ6bnsP6E/vpQKcghqoset5Kw0MtJJGeW/QeeNbcmaB7uJ71gQogSMLMCp1uF62RIYo0kSZiodT7fcp4f9kQC8P7IdjzRqzHLn7iPxZM708LdlpSsPBasj+D+D7fz2+HLhb7sVyeJ6TmsPHwZgKdqaS9YPkszDV+P74iVmYY95xP4Yuu5Aut/P3KZHK2OtvXtaeflYJwghbiDl6MVjV2t0eoU9l0oW2/YteRMDkQmAvBQexlmK4QoIZm0uUaTJEzUKj/sjuSTzWcBeO0hX0Z20s8vp1Kp6NvSjX+e7cmHo9pTz96CmOQs5vwexuDPd7EtIu6e1yIaw0/7LpGVq6NNfTsCmjgbO5xK19TNlrcfbgPAZ1vOsee8/kutoigsP6hPRqUXTFQ3vZq5ArCzjEMS84dNd2nkVGOvWxVCGIHhujDpCauJJAkTtcbvR67wxlr9B9Hs/s2Z0r3w/HIatYpHOnmx9T99mPdAS+wsTIiITWXKkkOM/W4/xy8nVXHUxcvK1fLjvigAnuzVpM5US3vYz4tH/b1RFHj212PEpWSx70ICkTfSsTE3Yaj0FIhqpldz/ZDEnWfjy/RjTv5cekOl2IwQojSkOEeNJkmYqBU2hMfywu/HAZja3YeZ/Zretb2FqYanejdh1wv381SvxpiZqNl/MZFhX+0h6JejRN1Ir4qw7+r3I1dISM/By9GSB9t4GDucKvX6sNa09LDlRloOM389xo/79GXph3Woh7V5tSzqKuqwrj7OmGpUXLmZyaWEjFJtez4ulZMxKZioVQxu61lJEQohaqXbhyNWw9E84u4kCRM13u5zN5i5/Bg6BUZ18uKVwa1K3Gtkb2XKvAdbse0/fRjZ0QuVCtaduEb/j3fw6ppwbqQVXaWvsml1Cot26cvSP97Dp9yTwNY0FqYavhrfEWszDfsvJrLhpBTkENWXtbmJoTz9znPxpdo2vxesd3NXHK3NKjw2IUQt5tQE1KaQkwbJl40djSiluvXNTtQ6R6Nv8uRPh8nR6hjU2oMFI9qiVpd+2F59B0s+Gt2ef2b2pE8LV/J0Cj/uu0Tv97fx2eZzpGfnlStOrU4/yfBHm86UqIJayKlYohIysLc0ZbS/d7mOXVM1cbXhnRFtDY87eDvQup69ESMSong9868LO1vy68IURZGhiEKIsjMxA5dm+r9lSGKNI0mYqLGORd9kyuJDZORo6dnMhc/Gdih3j1ErTzuWTOnCsie60t7LnvQcLZ9sPkvvD7bz0/5L5Gp1pd7n+bhURn2zl5dXh/PF1vMM/GQHIaeuF9teURT+d2ty5gn3NazTw++GdajP5G6NAJjeu3ZXhxQ1W35xjn0XbpT4cyL0chLRiRlYmWkY4OtemeEJIWorKc5RY0kSJmqk1ceu8Oi3+0nOzMWvgQPfPNYJcxNNhe2/WxMX/gzqzpfj/GjobMWNtGz++2c4gZ/sZP2JayW6+D5Xq+Orbed58LPdHI1OwsbchIbOVlxPyeaJHw8TvOwoCUUMdzx86SbHopMwM1Ez6VYCUpfNH9qa468OZFAbuV5GVF+t69nhZG1Geo6WY9FJJdomvxdsoK87VmZ198cWIUQ5SHGOGkuSMFGjaHUK766PYPaK4+Tk6ejfyp2fHu9aKb1FKpWKIe3qETK7N28Ma42ztRkXb6Qz45ejPPz1Xg5cTCh22/CryQz7cg8fbDxDjlZH3xaubJrdi42zejG9dxM0ahVrw/TXnq0JvVogqfvfDn0v2MiO9XG1Na/w86qJ7K1MjR2CEHelVqvo0VRfJXFXCa4Lu5qUyepj+gmah3WQCZqFEGVkKM4hPWE1TYUkYdnZ2Vy7do3ExMSK2J0QRUrNyuXJHw/zzY4LADzdpwnfTuiETSUP1zMzUTMxoBE7XujLzH7NsDLTEHo5iUe/3c/jSw5x9nqqoW1WrpYPNkYw7Ks9nLqWgoOVKZ882p4fJnemnoMlFqYaXnygJX8+3Z1WnnbczMjl2V9DeXzpYWKSMjkfl8bm09dRqWBaTxl+J0RN0rPZv6Xq7yY9O49pSw+TnJmLr6cdPW5tJ4QQpZbfExZ/FrTlu35dVK1yJWHffvstfn5+WFtb4+XlxX/+8x/DulWrVjFixAjOnz9f7iCFiE7IYOTCvWyJiMPcRM1nYzrwwqCWZSrCUVY25iY8N6A52+f04bH7GqBRq9gSEcegT3fywu/H2XzqOoM/38VX2y6g1SkMbutJyOzePOznVahaY1sve/4K7s7zA5pjplGzNSKOgZ/s5Pnf9GX2+7dyp4mrTZWdmxCi/PKLc4RdTeZmek6RbXQ6hVkrQjl9LQUXG3O+m+SPaR2rfiqEqEAOjcDEErTZcDPS2NGIUijTJ79Wq+Xhhx9mxowZnD59mlatWhW6RqZ9+/b8+eefrFixokICFXXX3gs3GPrVbs5eT8PN1pyVTwUYdfiOm60Fbw1vS8jsXjzQxgOdAisPX2Haj4e5EJ+Oi4053zzWka/Gd7zrcEJTjZpn+jVj3cwe+DVwIC07zzBZ9FO9pBdMiJrGw96C5u42KArsuVB0lcQPNp0h5NR1zEzU/G9CJ+o7WFZxlEKIWkWtBreW+r9lSGKNUqYk7Msvv2TNmjU88MADXLp0iRMnThRq06RJE5o2bcr69evLHaSou37af4mJ3x8kKSOX9l72/P1MD9p7Oxg7LAAau9qw8LFOrHq6G10aOQEwsqMXm5/rVaoiEs3cbfl9ejdeHeKLjbkJA33d8b+1PyFEzZJfJXFXEaXq/zhyhYXb9cOp3x/ZzjC3mBBClItba/29FOeoUcp0Mc2SJUtwd3dnxYoVWFtbF9vO19eXI0eOlDk4UXcpisL8v06ydN8lAIZ1qMd7I9thYVpxFRArSscGjqx46j7Sc7Rlvj5No1YxtYePoRy7EKJm6tnclUW7I9l5Lh5FUQxDkY9cSmTeKv0PlsF9mzLcT4pxCCEqiJSpr5HK1BN25swZunbtetcEDMDa2pr4+HtXiRLiTt/vjmTpvkuoVPDCoBZ8+miHapmA5VOpVBVSIEStVlXpdW5CiIrVpZETZiZqriVncSE+DYArNzN48scjhknlnxvQ3MhRCiFqFSlTXyOVKQkzNTUlKyvrnu2io6OxtbUtyyFEHXYoKpEF6yMAmP9Qa57u07RQYQshhKiOLM00huHJO8/eIO1WJcSE9Bxa17Pj40fbyw8tQoiKlV+mPuEC5N77+7moHsqUhLVu3ZojR46QmppabJu4uDhCQ0Pp0KFDWWMTddCNtGyClx1Fq1MY2r4eEwMaGjskIYQolV7N9SXnt5+N59nlx4iITcXV1pxFk/xlUmYhRMWz9QALB1C0cOOssaMRJVSmJGzChAkkJCQwffp0cnIKl+HVarUEBQWRkZHBpEmTyh2kqBu0OoWZy49xPSWbpm42LBjRVnrAhBA1Tn6p+p1n4w3Tanw30R9Pe6mEKISoBCrVbZM2y5DEmqJMSdiTTz5Jnz59WL58OS1atGD69OkAHD9+nGeffZbmzZvzxx9/MGDAAMaPH1+hAYva69PNZ9l7IQErMw0Lx3fEupInYRZCiMrQ0sMWF5t/p6f4YFR7OlSTqq5CiFpKinPUOGVKwjQaDf/88w8zZswgJiaGb7/9FoBjx47xxRdfEB0dzRNPPMGff/4pPRmiRLadieOLrfqJvReMaEszd7mWUAhRM6lUKh5s6wHAs/2aMbR9PSNHJISo9aQ4R42jUu6cZbmU4uPj2b59O1FRUeh0Ory8vOjbty/16tWN/3RSUlKwt7cnOTkZOzs7Y4dTI125mcGQL3aTlJHLhPsa8ubwNsYOSQghyiU7T8ulhAyayw9KQoiqELUHljwI9g1gduH5e0XVKWluUO7xXq6urowaNaq8uxF1VHaelqBfjhomY35lSCtjhySEEOVmbqKRBEwIUXXye8KSoyErBSykY6C6K9NwRJ1OR0pKCrm5ucW2yc3NJSUlBZ1OV+bgRO339rrTHL+SjL2lKV+N74i5SfWdC0wIIYQQolqycgIb/TBo4s8YNxZRImVKwj755BMcHR3ZsWNHsW127NiBo6MjX3zxRZmDE7XbmtCr/LjvEgCfPtoBL0crI0ckhBBCCFFDSXGOGqVMwxFXr16Nt7c3/fv3L7ZN//798fLy4o8//uDZZ58tc4Ci5rmcmMG3Oy+SmavFykyDpakGSzPNbX/rX3avrgkH4Jn7m9K3pZsxQxZCCCGEqNncfOHiNinOUUOUKQk7d+4c/v7+92zXpk0bjh49WpZDiBoqIS2bx74/wKWEjBK179bEmVn9m1dyVEIIIYQQtZz0hNUoZUrCkpOTsbe3v2c7e3t7bt68WZZDiBooK1fLtB8PcykhAy9HS8Z3bUhmTh4ZOVoyc7Vk5mjJyNGSkaslK0eLnaUJ745sh0Yt0xgIIYQQQpSLTNhco5QpCfP09CQsLOye7cLCwnBzk2FmdYFOpzB7RSjHopOwtzRlyZQuNHWzMXZYQgghhBB1g2sL/X16HKTfAGsX48Yj7qpMhTnuv/9+Tp8+zYoVK4pts3LlSk6dOkXfvn3LHJyoOd755zTrw2Mx06j5dkInScCEEEIIIaqSuQ04NNT/Lb1h1V6ZkrA5c+ZgZmbGxIkTCQ4OJiwsjPT0dNLT0wkLCyM4OJgJEyZgZmbGnDlzKjpmUc0s3RvFot2RAHwwqh1dGzsbOSIhhBBCiDrIMCRRrgur7sqUhLVs2ZIff/wRjUbDwoUL8fPzw87ODjs7O/z8/Pj666/RaDQsXbqUNm3aVHTMohoJOXWd1/8+CcCcwBYM61DfyBEJIYQQQtRR7reSsOvhxo1D3FOZkjCAUaNGERYWxlNPPUXTpk0xNzfH3Nycpk2bMmPGDI4fP86jjz5akbGKaub45SSeWX4UnQJju3jzdJ8mxg5JCCGEEKLucr/V+XH9pHHjEPdUpsIc+Zo2bcrXX39dUbGIGuRyYgaPLz1EVq6O3s1deXNYG1QqqXIohBBCCGE0hiTsFOi0oNYYNx5RrDL3hFWmBQsW0LlzZ2xtbXFzc2P48OGcOXPGsD4xMZFnnnmGFi1aYGlpSYMGDZg5cybJyckF9hMdHc3gwYOxsrLCzc2NOXPmkJeXV6DN9u3b6dixo6EXb8mSJVVxijVackYukxcf5EZaDr6ednw1viMmmmr5UhJCCCGEqDucm4CJJeRlQmKksaMRd1Etvznv2LGDoKAg9u/fT0hICLm5uQwcOJD09HQAYmJiiImJ4cMPPyQ8PJwlS5awYcMGHn/8ccM+tFotgwcPJicnh71797J06VKWLFnCq6++amgTGRnJ4MGD6du3L6GhocyaNYtp06axcePGKj/nmiI7T8uTPx3mQnw6nvYWLJ7SGRvzcnWoCiGEEEKIiqDW/Dtp8/UTxo1F3JVKURTlXo0aN26MSqVi8+bN+Pj40Lhx45IfQKXiwoUL5QoyPj4eNzc3duzYQa9evYps89tvv/HYY4+Rnp6OiYkJ69evZ8iQIcTExODu7g7AN998w9y5c4mPj8fMzIy5c+eybt06wsP/vXhxzJgxJCUlsWHDhhLFlpKSgr29PcnJydjZ2ZXrPKs7nU5h9spQ1oTGYGNuwu8zAmjpUbvPWQghhBCiRlkTDMd+gp7/gX7/NXY0dU5Jc4MSdWFERUUBkJubW+BxVckfZujk5HTXNnZ2dpiY6E9p3759tG3b1pCAAQQGBjJjxgxOnjyJn58f+/bto3///gX2ExgYyKxZs4o9TnZ2NtnZ2YbHKSkpZTmlGumjkDOsCY3BRK1i4WMdJQETQgghhKhuPNrq76U4R7VWouGIOp0OnU5H8+bNCzwu6a08dDods2bNonv37sWWu79x4wZvvvkmTz75pGFZbGxsgQQMMDyOjY29a5uUlBQyMzOLPNaCBQuwt7c33Ly9vct8bjXJ8oPRfLVN36P5zoi29GzmauSIhBBCCCFEIe6t9fdSpr5aq5bXhN0uKCiI8PBwfv311yLXp6SkMHjwYHx9fZk/f36lxzNv3jySk5MNt8uXL1f6MY1t+5k4XvlT/0aeeX9TRvvXjcRTCCGEEKLGyU/Cki9DZpJRQxHFK1MS5uTkRO/evSs6lkKCg4NZu3Yt27Ztw8vLq9D61NRUBg0ahK2tLatXr8bU1NSwzsPDg+vXrxdon//Yw8Pjrm3s7OywtLQsMiZzc3PDxNT5t9rsZEwyQb8cRatTGOFXn9kDmhs7JCGEEEIIURxLR7C/9YO5DEmstsqUhOXl5RWZFFUURVEIDg5m9erVbN26FR8fn0JtUlJSGDhwIGZmZvz1119YWFgUWB8QEMCJEyeIi4szLAsJCcHOzg5fX19Dmy1bthTYLiQkhICAgEo4q5onJimTqUsOkZ6jJaCxM++ObCdzgQkhhBBCVHeGIYmShFVXZUrCWrduzdWrVys6FoOgoCB+/vlnli1bhq2tLbGxscTGxhqu08pPwNLT0/n+++9JSUkxtNFqtQAMHDgQX19fJkyYwPHjx9m4cSOvvPIKQUFBmJubAzB9+nQuXrzICy+8QEREBF9//TUrV65k9uzZlXZuNUVqVi5Tlxzieko2zdxs+GZCJ8xMqv3oVSGEEEIIYZi0WcrUV1dl+lb9zDPPsHv3bnbv3l3R8QCwcOFCkpOT6dOnD56enobbihUrADh69CgHDhzgxIkTNG3atECb/Gu0NBoNa9euRaPREBAQwGOPPcbEiRN54403DMfx8fFh3bp1hISE0L59ez766CMWLVpEYGBgpZxXTZGr1fH0L0eJiE3F1dacxVM6Y29peu8NhRBCCCGE8UlPWLVXonnC7hQdHc0777zDTz/9xLRp03jooYdo0KBBoSGB+Ro0aFDuQKur2jZPmKIozP0jjJWHr2BpqmHlUwG09bI3dlhCCCGEEKKkbpyDL/3BxBJeuqqfxFlUiZLmBmVKwtRqNSqVCkVR7nmNkEqlIi8vr7SHqDFqWxL2xZZzfBRyFrUKvpvoT79W7vfeSAghhBBCVB86LbxTH/IyIfgIuDQ1dkR1RoVO1nynXr16SYGGWmj1sSt8FHIWgNeHtZEETAghhBCiJlJrwK0VxBzVXxcmSVi1U6YkbPv27RUchjC2vRdu8MLvYQA81asxE+5raOSIhBBCCCFEmXm00SdhseHQ+mFjRyPuIOXuBOeup/LUT0fI1SoMbufJ3EEtjR2SEEIIIYQoD0OFRCnOUR2VOAlLTk7mhRdeoHnz5lhaWuLg4ECvXr349ddfKzM+UcniUrOYvPgQqVl5+Dd05KNR7VGrZaipEEIIIUSNZkjCwo0bhyhSiYYjpqam0q1bNyIiIsiv45Gdnc3u3bvZs2cPp06dKlD6XdQM6dl5PL7kMFeTMvFxsebbif5YmEr1HCGEEEKIGs/dV3+ffBkyk8DSwZjRiDuUqCfsgw8+4PTp0zRs2JClS5cSFhbGnj17mDt3LqamprzzzjtcvHixsmMVFShPq2Pm8mOcuJqMk7UZiyd3xsnazNhhCSGEEEKIimDpCPbe+r9lSGK1U6KesDVr1mBtbc22bdto2PDfgg0BAQG4uLgwZ84c/vrrL2bNmlVZcYoKpCgKr/99ii0RcZibqPluoj+NXKyNHZYQQgghhKhI7q31PWHXT0Kj7saORtymRD1hFy9epFu3bgUSsHzjxo0D4Pz58xUbmag03+26yE/7L6FSwaePdqBTQ0djhySEEEIIISqa4bqwE8aNQxRSoiQsPT2d+vXrF7nO09MTgMzMzIqLSlSadWHXeOefCABefrAVD7T1NHJEQgghhBCiUnhIhcTqqsJK1OcX7BDV1+GoRGavDAVgUkBDHu/hY9yAhBBCCCFE5TH0hJ0Cnda4sYgCSjxZc2xsLDt37izT+l69epU+MlGhIm+k88SPh8nJ09G/lTuvPtQalUpK0QshhBBC1FpOjcHEEvIyITESXJoaOyJxi0opQReWWq2+6xd2RVGKXa9SqcjLyyt7hNVcSkoK9vb2JCcnY2dnZ+xwipSQls2IhXu5lJBBOy97fn3yPqzMSpx/CyGEEEKImurbvhBzFEYtgdYPGzuaWq+kuUGJvon36tVLek1qqKxcLU/8eJhLCRl4OVry/aTOkoAJIYQQQtQVHm30SVhsuCRh1UiJvo1v3769ksMQlUGnU5i9IpSj0UnYWZiwZEpnXG3NjR2WEEIIIYSoKu5SnKM6qrDCHKL6WbD+NOvDYzHTqPl2oj9N3WyNHZIQQgghhKhKhiQs3LhxiAIkCaulftwXxXe7IgH4YFQ77mvsbOSIhBBCCCFElXNvrb9PvgyZSUYNRfxLkrBaaPOp68z/S9/lPCewBcM6FD3HmxBCCCGEqOUsHcDeW/+3DEmsNiQJq2XCriTxzPJj6BQY09mbp/s0MXZIQgghhBDCmOS6sGpHkrBa5HJiBlOXHCYzV0uv5q68ObyNVLUUQgghhKjr8ockXj9h3DiEgSRhtURyRi5TlhziRlo2LT1s+WqcH6Ya+ecVQgghhKjzPKQnrLqRb+m1xIrD0ZyPS8PDzoLFUzpja2Fq7JCEEEIIIUR1YBiOeAp0WuPGIoASzhN2p5SUlLvOAH270NBQOnToUJbDiFJ4omdjcvJ09Gvljqe9pbHDEUIIIYQQ1YVTYzCxhLxMSIwEl6bGjqjOK1NP2JAhQ8jKyrpnuyNHjtC/f/+yHEKUkkqlIvj+ZrTyLFlyLIQQQggh6gi1Btx99X/LdWHVQpmSsN27dzNq1Ci02uK7Mw8fPsyAAQNISUkpc3BCCCGEEEKICpBfnCNWJm2uDsqUhM2cOZN169YxefLkItcfPHiQAQMGkJaWxrJly8oTnxBCCCGEEKK83Nvq76U4R7VQpmvCPv30UxITE/nll19wdHTk888/N6zbv38/gYGBZGZm8uuvvzJixIgKC1YIIYQQQghRBoYy9dITVh2UKQkDWLx4MTdv3uSrr77CycmJ+fPns2fPHh544AGys7NZuXIlw4cPr8BQhRBCCCGEEGWSn4QlX4bMJLB0MGY0dV6ZkzCNRsNvv/3GwIEDefPNN7lx4wY//fSTIQEbNmxYRcYphBBCCCGEKCtLB7BvAMnR+iGJjbobO6I6rVzzhFlYWLB27VratWvHwoULycnJ4Y8//pAETAghhBBCiOrGMCRRrgszthL1hP344493XT9u3DhOnjzJ8OHDSUxMLNR+4sSJZY9QCCGEEEIIUX4ebeDseilTXw2oFEVR7tVIrVajUqnu2kZRlEJt8pfdrZR9TZeSkoK9vT3JycklnsBaCCGEEEKIKndyNfw2Gep3gie2GjuaWqmkuUGJesJeffXVeyZhQgghhBBCiGrMUKb+FOi0+kmchVGUKAmbP39+JYchhBBCCCGEqFROPmBqBbkZkHABXJsbO6I6q1yFOSrLggUL6Ny5M7a2tri5uTF8+HDOnDlToM23335Lnz59sLOzQ6VSkZSUVGg/iYmJjB8/Hjs7OxwcHHj88cdJS0sr0CYsLIyePXtiYWGBt7c377//fmWemhBCCCGEEMah1oBHO/3fMUeNG0sdV6Yk7Pr16/z1119ERkYW2yYyMpK//vqLuLi4Uu9/x44dBAUFsX//fkJCQsjNzWXgwIGkp6cb2mRkZDBo0CBeeumlYvczfvx4Tp48SUhICGvXrmXnzp08+eSThvUpKSkMHDiQhg0bcuTIET744APmz5/Pt99+W+qYhRBCCCGEqPbqd9TfX5UkzJhKVJjjTnPnzuXDDz8kPDycVq1aFdnm1KlTtG3blhdffJG33367XEHGx8fj5ubGjh076NWrV4F127dvp2/fvty8eRMHBwfD8tOnT+Pr68uhQ4fw9/cHYMOGDTz44INcuXKFevXqsXDhQl5++WViY2MxMzMD4MUXX+TPP/8kIiKiRLFJYQ4hhBBCCFFjhP0Gq6aBV2eYttnY0dQ6Jc0NytQTtn79elq3bl1sAgbg6+tL69atWbduXVkOUUBycjIATk5OJd5m3759ODg4GBIwgP79+6NWqzlw4IChTa9evQwJGEBgYCBnzpzh5s2b5Y5bCCGEEEKIaiW/J+xaGOTlGDeWOqxMSdilS5do3vzeF/I1a9aM6OjoshzCQKfTMWvWLLp3706bNm1KvF1sbCxubm4FlpmYmODk5ERsbKyhjbu7e4E2+Y/z29wpOzublJSUAjchhBBCCCFqBKfGYOEA2myIO2XsaOqsMiVhJZ33S6VSkZ2dXZZDGAQFBREeHs6vv/5arv1UlAULFmBvb2+4eXt7GzskIYQQQgghSkalgnp++r+lOIfRlCkJa9y4Mfv27SMvL6/YNnl5eezbt48GDRqUObjg4GDWrl3Ltm3b8PLyKtW2Hh4ehYqC5OXlkZiYiIeHh6HN9evXC7TJf5zf5k7z5s0jOTnZcLt8+XKp4hJCCCGEEMKo6nfS3189Ytw46rAyJWEPPfQQsbGxvPjiixRX12PevHnExsYydOjQUu9fURSCg4NZvXo1W7duxcfHp9T7CAgIICkpiSNH/n1xbd26FZ1OR9euXQ1tdu7cSW5urqFNSEgILVq0wNHRscj9mpubY2dnV+AmhBBCCCFEjWGokHjMuHHUYWWqjpiYmEj79u2JiYmhTZs2PP744zRp0gSACxcu8P333xMeHo6HhwfHjx/HxcWlVPt/+umnWbZsGWvWrKFFixaG5fb29lhaWgL6a7ZiY2M5fPgwTzzxBDt37sTW1pYGDRoYCng88MADXL9+nW+++Ybc3FymTJmCv78/y5YtA/QFP1q0aMHAgQOZO3cu4eHhTJ06lU8++aRAKfu7keqIQgghhBCiRkm5Bh+3BJUa5l0BM2tjR1RrlDQ3KFMSBvoS8A8//DBnz55FpVIVWKcoCs2bN+ePP/6gdevWpd73nfvLt3jxYiZPngzA/Pnzef311+/aJjExkeDgYP7++2/UajUjR47k888/x8bGxtA+LCyMoKAgDh06hIuLC8888wxz584tcayShAkhhBBCiBrno1aQGgNT1kPDbsaOptao9CQM9AU6Vq1axebNmw3XRnl7e9O/f39GjBiBRqMp665rDEnChBBCCCFEjfPreIhYCwPfhm7Bxo6m1ihpbmBSnoNoNBpGjRrFqFGjyrMbIYQQQgghRFWq56dPwqRColGUqTCHEEIIIYQQogaTColGVa4kLCwsjKeeegpfX1/DvFm+vr5Mnz6dsLCwiopRCCGEEEIIUZHy5wq7GQUZiUYNpS4qcxL22Wef4e/vz6JFi4iIiCA1NZXU1FQiIiL49ttv8ff357PPPqvIWIUQQgghhBAVwdIBnPTVzWVIYtUrUxIWEhLC7NmzMTMzY/bs2Rw7doybN2+SlJREaGgozz//PObm5jz33HNs2bKlomMWQgghhBBClJdhSKIkYVWtTEnYxx9/jImJCZs2beLDDz+kffv22NvbY2dnR7t27fjggw/YtGkTarWajz76qKJjFkIIIYQQQpSXYdJmScKqWpmSsIMHD9K7d2+6dSt+ToGAgAD69OnDgQMHyhycEEIIIYQQopLUy0/CjkDZZ60SZVCmJCwjIwNXV9d7tnN1dSUjI6MshxBCCCGEEEJUJs92oNJAehykXDV2NHVKmZIwb29v9u3bR15eXrFt8vLy2LdvH97e3mUOTgghhBBCCFFJTC3B3Vf/twxJrFJlSsKGDRvGpUuXmDp1KklJSYXWp6Sk8MQTTxAdHc3w4cPLGaIQQgghhBCiUuQPSZQKiVVKpSilHwCamJhI586diYqKwsbGhkGDBtGoUSMALl26xIYNG0hJSaFx48YcOnQIR0fHio672khJScHe3p7k5GTs7OyMHY4QQgghhBAld2QJ/P0s+PSCSX8bO5oar6S5gUlZdu7k5MSuXbt46qmnWLduHb/99luhNoMHD+Z///tfrU7AhBBCCCGEqNHyy9THhIJOB+oyTyMsSqFMSRhAvXr1+Pvvv4mMjGT37t3ExMQYlvfo0QMfH58KC1IIIYQQQghRCVxbgYklZKdA4gVwaWbsiOqEMidh+Xx8fCThEkIIIYQQoibSmOirJF4+oC9VL0lYlShTf2Pjxo2ZO3fuPdvNmzePJk2alOUQQgghhBBCiKqQPyRRKiRWmTIlYVFRUcTHx9+z3Y0bN4iKiirLIYQQQgghhBBVQSokVrlKvfIuPT0dU1PTyjyEEEIIIYQQojzq30rCroVBXo5xY6kjKiUJ0+l0nD59mm3bttGgQYPKOIQQQgghhBCiIjg1Bgt70GZD3CljR1MnlDgJ02g0hhvA0qVLCyy7/WZqakqbNm24fv06Y8eOrbTghRBCCCGEEOWkUsmQxCpW4uqI3t7eqFQqAKKjo7GyssLFxaXItmZmZtSrV4+hQ4cyc+bMiolUCCGEEEIIUTnqd4SL2/QVEv2nGjuaWq/ESdjtBTbUajWjRo3ihx9+qIyYhBBCCCGEEFXJUCHxmHHjqCPKNE/Ytm3b8PDwqOhYhBBCCCGEEMaQPxwx/jTkpIOZtXHjqeXKVJijd+/etGjRotDyrKwsYmNjycvLK3dgQgghhBBCiCpi5wm2nqDo4NpxY0dT65UoCUtNTeXgwYOcPXu2yPXnzp0jMDAQOzs76tevj62tLWPGjOHatWsVGqwQQgghhBCiksikzVWmREnYjz/+SEBAAGvXri20LjY2lp49e7J582by8vJQFIXs7Gx+++03+vbtS2ZmZoUHLYQQQgghhKhg9fz091IhsdKVKAnbsWMHarWaxx57rNC6N998k7i4OBwdHVmzZg2pqakcPXoUf39/zp07x8KFCys8aCGEEEIIIUQFy5+0+eoR48ZRB5QoCQsLC6Nt27a4ubkVWK7T6Vi+fDkqlYp33nmHhx56CGtrazp06MCqVaswMTHhzz//rIy4hRBCCCGEEBUpvyfsZhRkJBo1lNquRElYXFxckYU4wsLCSEpKwsTEhDFjxhRYV79+fbp27crp06crJlIhhBBCCCFE5bF0BKcm+r9lSGKlKlESlp6eTm5ubqHlR47ouyrbtWuHnZ1dofVeXl6kpKSUM0QhhBBCCCFElTAMSZQkrDKVKAlzdXUlIiKi0PLdu3ejUqno0qVLkdtlZWVhb29fvgiFEEIIIYQQVUMqJFaJEiVh+cMK//77b8Oy+Ph4Vq1aBcDAgQOL3O7UqVPUq1evAsIUQgghhBBCVLr8JOzKQdDpjBtLLVaiJCw4OBhFURg1ahQTJ07k+eefp3PnzqSmpuLt7c3gwYMLbXPx4kXOnj1L+/btKzxoIYQQQgghRCXw7ACmVpCRAPGFR8KJilGiJKxv377Mnz+f3Nxcfv75Zz799FOio6OxtLRk8eLFmJiYFNrmm2++ASAwMLBiIxZCCCGEEEJUDhMz8O6q/ztql3FjqcUKZ0/FePXVVxkyZAirVq0iPj4eb29vxo8fj4+PT5Htzc3NefbZZxk0aFCFBSuEEEIIIYSoZD494eI2fRLW9SljR1MrqRRFUYwdRE2WkpKCvb09ycnJRVaIFEIIIYQQoka5fBC+H6AvWT/nIqhLNHhOUPLcoFo+owsWLKBz587Y2tri5ubG8OHDOXPmTIE2WVlZBAUF4ezsjI2NDSNHjuT69esF2kRHRzN48GCsrKxwc3Njzpw55OXlFWizfft2OnbsiLm5OU2bNmXJkiWVfXpCCCGEEEJUX/X8wNQaMm9C3CljR1MrVcskbMeOHQQFBbF//35CQkLIzc1l4MCBpKenG9rMnj2bv//+m99++40dO3YQExPDiBEjDOu1Wi2DBw8mJyeHvXv3snTpUpYsWcKrr75qaBMZGcngwYPp27cvoaGhzJo1i2nTprFx48YqPV8hhBBCCCGqDY0pNLhP/3fUbuPGUkvViOGI8fHxuLm5sWPHDnr16kVycjKurq4sW7aMRx55BICIiAhatWrFvn37uO+++1i/fj1DhgwhJiYGd3d3QF8sZO7cucTHx2NmZsbcuXNZt24d4eHhhmONGTOGpKQkNmzYUKLYZDiiEEIIIYSodXZ9DFteh5ZDYMwvxo6mxqjRwxHvlJycDICTkxMAR44cITc3l/79+xvatGzZkgYNGrBv3z4A9u3bR9u2bQ0JGOgrNaakpHDy5ElDm9v3kd8mfx9Fyc7OJiUlpcBNCCGEEEKIWsWnl/4+arfMF1YJqn0SptPpmDVrFt27d6dNmzYAxMbGYmZmhoODQ4G27u7uxMbGGtrcnoDlr89fd7c2KSkpZGZmFhnPggULsLe3N9y8vb3LfY5CCCGEEEJUK57twcwGspLgevg9m4vSqfZJWFBQEOHh4fz666/GDgWAefPmkZycbLhdvnzZ2CEJIYQQQghRsTSm0CBA/7dcF1bhqnUSFhwczNq1a9m2bRteXl6G5R4eHuTk5JCUlFSg/fXr1/Hw8DC0ubNaYv7je7Wxs7PD0tKyyJjMzc2xs7MrcBNCCCGEEKLWadRDfy+TNle4apmEKYpCcHAwq1evZuvWrYUmhO7UqROmpqZs2bLFsOzMmTNER0cTEKDP2AP+3969x8lc9/8ff84esXZX67S2ZSOJzZlk1aX8EkkOOaSUUyo5JIdUXKhvKp1dKZUuSl0loUROkUgO5bQ25JBTZLFYdll7nHn//th2sqGGZuczs/O432572zGfz+y+xus979nnfE4JCdqyZYtSUlKc6yxdulQRERGKj493rnPuzyhYp+BnAAAAAH6r6r/yv/+6WnLYra2lmPHKEDZw4EB9/PHHmj59usLDw3XkyBEdOXLEeZxWZGSk+vbtq2HDhmn58uXauHGj+vTpo4SEBDVtmn86zVatWik+Pl49evRQUlKSvv76a40ePVoDBw5UaGioJOmRRx7R3r179cQTT2jHjh16++23NXPmTA0dOtSy5w4AAAB4heh6Uki4lJUmHdlidTXFileGsHfeeUdpaWm65ZZbVKlSJefXZ5995lxnwoQJuvPOO9W5c2c1b95c0dHR+uKLL5zLAwMDNX/+fAUGBiohIUH333+/evbsqWeffda5TtWqVbVgwQItXbpU9erV02uvvaYpU6aodevWHn2+AAAAgNcJDJLimuXf5rgwt/KJ64R5M64TBgAAgGJr9URp6Ripxu1S98/+fn0/V6yuEwYAAADAAs7jwtZwXJgbEcIAAAAAXFh0XSk0QspOlw4nWV1NsUEIAwAAAHBhAYEcF1YECGEAAAAALu6q33dJ5HphbkMIAwAAAHBxBRdt/nWtZM+ztpZighAGAAAA4OKi60glIqWc0xwX5iaEMAAAAAAXFxAoxd2Yf5tdEt2CEAYAAADgr3FcmFsRwgAAAAD8tYLjwg78INlzra2lGCCEAQAAAPhrFWtLJcpIOWc4LswNCGEAAAAA/lpAwB9bw/attLaWYoAQBgAAAODvOY8L46LN/xQhDAAAAMDf47gwtyGEAQAAAPh7FeKlklFSboaUnGh1NT6NEAYAAADg7wUESFf9fr0wjgv7RwhhAAAAAFzDcWFuQQgDAAAA4JqCEHbwRykvx9pafBghDAAAAIBryteUSpWVcs9KyZusrsZnEcIAAAAAuIbrhbkFIQwAAACA66q1yP++c5G1dfgwQhgAAAAA1117hyRb/u6IaYesrsYnEcIAAAAAuC68ohR7ff7tnQutrcVHEcIAAAAAXJqabfO/71hgbR0+ihAGAAAA4NLUvDP/+/7vpcxTlpbiiwhhAAAAAC5Nuer5p6t35Em/LLW6Gp9DCAMAAABw6Zy7JM63tg4fRAgDAAAAcOkKQtjub6TcLGtr8TGEMAAAAACXrlIDKTxGyjnDhZsvESEMAAAAwKULCJBq3pF/m10SLwkhDAAAAMDlKdglcedCyWG3thYfQggDAAAAcHnibpJCI6WMY9JvG6yuxmcQwgAAAABcnqAQqUar/NvskugyQhgAAACAy3fuqeqNsbYWH0EIAwAAAHD5qreUAkOk1L3SsZ1WV+MTvDKErVy5Uu3atVNMTIxsNpu+/PLLQsuPHj2q3r17KyYmRqVKldLtt9+uX375pdA6WVlZGjhwoMqWLavSpUurc+fOOnr0aKF1Dhw4oLZt26pUqVKqUKGCRowYoby8vKJ+egAAAEDxERouVbsl/za7JLrEK0NYRkaG6tWrp0mTJp23zBijjh07au/evZo7d64SExMVFxenli1bKiMjw7ne0KFD9dVXX2nWrFn67rvvlJycrE6dOjmX2+12tW3bVjk5OVqzZo0+/PBDTZs2TWPHjvXIcwQAAACKDecuiQusrcNH2Izx7h03bTab5syZo44dO0qSdu3apWuvvVZbt27VddddJ0lyOByKjo7WCy+8oAcffFBpaWkqX768pk+fri5dukiSduzYoVq1amnt2rVq2rSpFi1apDvvvFPJycmqWLGiJOndd9/Vk08+qWPHjikkJMSl+tLT0xUZGam0tDRFRES4/z8AAAAA8Hanj0qvXSvJSEN/liKvtLoiS7iaDbxyS9hfyc7OliSVKFHCeV9AQIBCQ0O1atUqSdLGjRuVm5urli1bOtepWbOmqlSporVr10qS1q5dqzp16jgDmCS1bt1a6enp2rZtmyeeCgAAAFA8hFeUKjfJv71zobW1+ACfC2EFYWrkyJE6efKkcnJy9NJLL+m3337T4cOHJUlHjhxRSEiIypQpU+ixFStW1JEjR5zrnBvACpYXLLuY7OxspaenF/oCAAAA/B67JLrM50JYcHCwvvjiC+3atUtRUVEqVaqUli9frjZt2iggoOifzvjx4xUZGen8qly5cpH/TgAAAMDr1bwz//v+76XMU5aW4u18LoRJUqNGjbR582adOnVKhw8f1uLFi3XixAlVq1ZNkhQdHa2cnBydOnWq0OOOHj2q6Oho5zp/Pltiwb8L1rmQkSNHKi0tzfl18OBBNz4zAAAAwEeVvVoqX1Ny5Em/LLW6Gq/mkyGsQGRkpMqXL69ffvlFGzZsUIcOHSTlh7Tg4GAtW7bMue7OnTt14MABJSQkSJISEhK0ZcsWpaSkONdZunSpIiIiFB8ff9HfGRoaqoiIiEJfAAAAAFT4ws24qCCrC7iQM2fOaPfu3c5/79u3T5s3b1ZUVJSqVKmiWbNmqXz58qpSpYq2bNmixx57TB07dlSrVq0k5Yezvn37atiwYYqKilJERIQeffRRJSQkqGnTppKkVq1aKT4+Xj169NDLL7+sI0eOaPTo0Ro4cKBCQ0Mted4AAACAT6vZVvr+NWn3N1JulhRc4u8f44e8MoRt2LBBLVq0cP572LBhkqRevXpp2rRpOnz4sIYNG6ajR4+qUqVK6tmzp8aMGVPoZ0yYMEEBAQHq3LmzsrOz1bp1a7399tvO5YGBgZo/f7769++vhIQEhYWFqVevXnr22Wc98yQBAACA4qZSAyk8RjqdLO1bKdVoZXVFXsnrrxPm7bhOGAAAAHCOBcOl9VOkhr2k9hOtrsajiu11wgAAAAB4sYLjwnYulBx2a2vxUoQwAAAAAO4Td5MUGillHJMO/GB1NV6JEAYAAADAfYJCpPh2+bc3f2JtLV6KEAYAAADAvRr0yP++bY6UlW5tLV6IEAYAAADAvSrfIJW9Rso9mx/EUAghDAAAAIB72WxSw9+3hiX+z9pavBAhDAAAAID71b1HsgVKv62XUnZYXY1XIYQBAAAAcL/wilKN2/NvszWsEEIYAAAAgKJRsEti0gwpL8faWrwIIQwAAABA0ah+m1S6onT2uLRrsdXVeA1CGAAAAICiERgk1bs3/za7JDoRwgAAAAAUnYJrhu3+RkpPtrYWL0EIAwAAAFB0ylWXqjSTjEPaPN3qarwCIQwAAABA0XJeM+xjyeGwthYvQAgDAAAAULTiO0gh4dLJfdKBNVZXYzlCGAAAAICiFRIm1e6Uf3sTJ+gghAEAAAAoeg175n//ea6UlWZtLRYjhAEAAAAoelc2ksrXkvIypa2fW12NpQhhAAAAAIqezSY1uD//tp/vkkgIAwAAAOAZ9e6RAoKl5E3S0W1WV2MZQhgAAAAAzwgrJ13bJv924sfW1mIhQhgAAAAAz2nw+zXDkmZIednW1mIRQhgAAAAAz6l+qxQeI2WmSjsXWl2NJQhhAAAAADwnIFCq3z3/tp+eoIMQBgAAAMCzGtwvySbtWSYd/8XqajyOEAYAAADAs6KqStfekX97zZvW1mIBQhgAAAAAz7txcP73pBnSmRRra/EwQhgAAAAAz6t8gxR7vWTPln6cbHU1HkUIAwAAAOB5NpvU7PetYeunSNlnrK3HgwhhAAAAAKxRs60UVU3KOiVt/sTqajyGEAYAAADAGgGBUsKg/Ntr35LsedbW4yGEMAAAAADWqd9dKlVWOnVA2j7X6mo8ghAGAAAAwDrBJaUmD+ffXj1RMsbaejyAEAYAAADAWtc/JAWVlA5vlvavsrqaIkcIAwAAAGCtsLJSg/vyb6+ZaG0tHuCVIWzlypVq166dYmJiZLPZ9OWXXxZafubMGQ0aNEixsbEqWbKk4uPj9e677xZaJysrSwMHDlTZsmVVunRpde7cWUePHi20zoEDB9S2bVuVKlVKFSpU0IgRI5SX5x8HAwIAAABepekASTbplyVSynarqylSXhnCMjIyVK9ePU2aNOmCy4cNG6bFixfr448/1vbt2zVkyBANGjRI8+bNc64zdOhQffXVV5o1a5a+++47JScnq1OnTs7ldrtdbdu2VU5OjtasWaMPP/xQ06ZN09ixY4v8+QEAAAD4k7JXS7Xa5d9e86a1tRQxmzHefeSbzWbTnDlz1LFjR+d9tWvXVrdu3TRmzBjnfY0aNVKbNm303HPPKS0tTeXLl9f06dPVpUsXSdKOHTtUq1YtrV27Vk2bNtWiRYt05513Kjk5WRUrVpQkvfvuu3ryySd17NgxhYSEuFRfenq6IiMjlZaWpoiICPc9cQAAAMDf/LZBmnKrFBAsDflJioixuqJL4mo28MotYX+nWbNmmjdvng4dOiRjjJYvX65du3apVatWkqSNGzcqNzdXLVu2dD6mZs2aqlKlitauXStJWrt2rerUqeMMYJLUunVrpaena9u2bRf93dnZ2UpPTy/0BQAAAMANYhtLVRIkR67042SrqykyPhnC3nzzTcXHxys2NlYhISG6/fbbNWnSJDVv3lySdOTIEYWEhKhMmTKFHlexYkUdOXLEuc65AaxgecGyixk/frwiIyOdX5UrV3bjMwMAAAD8XLPB+d83fCBln7a2liLisyHshx9+0Lx587Rx40a99tprGjhwoL755psi/90jR45UWlqa8+vgwYNF/jsBAAAAv1HjdqlcDSk7Tdr4odXVFIkgqwu4VJmZmRo1apTmzJmjtm3bSpLq1q2rzZs369VXX1XLli0VHR2tnJwcnTp1qtDWsKNHjyo6OlqSFB0drXXr1hX62QVnTyxY50JCQ0MVGhrq5mcFAAAAQJIUECAlDJK+Giz98I50Qz8pMNjqqtzK57aE5ebmKjc3VwEBhUsPDAyUw+GQlH+SjuDgYC1btsy5fOfOnTpw4IASEhIkSQkJCdqyZYtSUlKc6yxdulQRERGKj4/3wDMBAAAAcEF1u0lhFaT036StX1hdjdt55ZawM2fOaPfu3c5/79u3T5s3b1ZUVJSqVKmim2++WSNGjFDJkiUVFxen7777Th999JFef/11SVJkZKT69u2rYcOGKSoqShEREXr00UeVkJCgpk2bSpJatWql+Ph49ejRQy+//LKOHDmi0aNHa+DAgWzpAgAAAKwUXEK64WHp2+ekVa9LdbpIAYFWV+U2XnmK+hUrVqhFixbn3d+rVy9NmzZNR44c0ciRI7VkyRKlpqYqLi5ODz/8sIYOHSqbzSYp/2LNw4cP16effqrs7Gy1bt1ab7/9dqFdDX/99Vf1799fK1asUFhYmHr16qUXX3xRQUGuZ1NOUQ8AAAAUgaw06T918r93npofxLycq9nAK0OYLyGEAQAAAEXku5el5c9L5a6VBqz1+q1hxfo6YQAAAAD8wA39pBKR0vGd0rY5VlfjNoQwAAAAAN6pRKSU8Gj+7e9ekhx2a+txE0IYAAAAAO91Qz+pRBnp+K5ic6ZEQhgAAAAA71UiQmo2KP92MdkaRggDAAAA4N2a9JNKXiGd+EXaMtvqav4xQhgAAAAA71YiQmr2+7FhK1+W7HnW1vMPEcIAAAAAeL8mD0slo6QTu6Wtvr01jBAGAAAAwPuFhv+xNey7l3x6axghDAAAAIBvaPJQ/taw1L3SlllWV3PZCGEAAAAAfENouHTj4PzbPnxsGCEMAAAAgO+4/iGpVNnft4bNtLqay0IIAwAAAOA7QktLzX7fGvadb24NI4QBAAAA8C1NHpJKlZNO7pN+mmF1NZeMEAYAAADAt4SESTc+ln975SuSPdfaei4RIQwAAACA77m+rxRWXjq5X0ryra1hhDAAAAAAvqdga1i1FlKFeKuruSRBVhcAAAAAAJel6cA/LuDsQ9gSBgAAAMA3BfhmnPHNqgEAAADARxHCAAAAAMCDCGEAAAAA4EGEMAAAAADwIEIYAAAAAHgQIQwAAAAAPIgQBgAAAAAeRAgDAAAAAA8ihAEAAACABxHCAAAAAMCDCGEAAAAA4EGEMAAAAADwIEIYAAAAAHhQkNUF+DpjjCQpPT3d4koAAAAAWKkgExRkhIshhP1Dp0+fliRVrlzZ4koAAAAAeIPTp08rMjLyostt5u9iGv6Sw+FQcnKywsPDZbPZLK0lPT1dlStX1sGDBxUREWFpLSg69BmuYqwUf/QY7sR48g/0uWgZY3T69GnFxMQoIODiR36xJewfCggIUGxsrNVlFBIREcGLyg/QZ7iKsVL80WO4E+PJP9DnovNXW8AKcGIOAAAAAPAgQhgAAAAAeBAhrBgJDQ3V008/rdDQUKtLQRGiz3AVY6X4o8dwJ8aTf6DP3oETcwAAAACAB7ElDAAAAAA8iBAGAAAAAB5ECAMAAAAADyKEAQAAAIAHEcIAAAAAwIMIYXAJJ9Es/lJSUqwuAT6EOaH4Y06AuzFvFH/Jyck6fvy41WX4BEIY/tKZM2eUm5srm83G5FmMJSYmKjo6WitXrrS6FHg55gT/wJwAdzp58qQyMzOZN4q5xMRExcbGat26dVaX4hMIYbio7du366677tJnn32mnJwcJs9iKikpSTfffLOGDh2q5s2bW10OvBhzgn9gToA7bd++Xa1atdIrr7yis2fPMm8UU0lJSWrevLmGDh2qO+64w+pyfEKQ1QXAO/3666/q3Lmz9uzZozNnzqhEiRJq3769QkJCZIyRzWazukS4wdatW9WsWTMNGzZM48aNkzFGu3fvVnJysmrUqKFKlSpZXSK8BHOCf2BOgDsdOHBA9957r44cOaKvv/5aJUuW1MCBA1WqVCnmjWJk69atuummmzRo0CCNHz9eDodDGzdu1KFDh1SlShU1bNjQ6hK9ElvCcB673a7PP/9c1atX17p161SmTBm98MILmjdvHp9+FyPZ2dkaPXq0MjMzNW7cOEnSnXfeqW7duqlFixZq166dhgwZYm2R8ArMCf6BOQHuZIzRokWLFB0drQULFqhu3bqaNWuWJk2a5Nwi5nA4rC4T/5DD4dCLL76ojIwMjRo1SpJ0++23a8CAAerSpYt69Oihu+66y+IqvZPN8M6JC9i8ebN2796tLl26yOFwqG3btjp69KhGjRqldu3aKTQ0lE+xfJwxRuvXr1efPn1UunRpRUREqGTJknrssccUHR2t2bNna86cOerUqZPGjh1rdbmwGHNC8cecAHc7fPiwfvjhB+cf4f3799fGjRvVtWtXDRgwQGFhYcwbxcDx48fVsWNHHTt2TOXLl1dUVJTGjh2rqKgorV69Wi+++KKaNm2qqVOnWl2qVyGE4YJyc3MVHBzs/HdOTo46dOjg/KOrQ4cOCg4O1ty5c9WhQwcLK8XlOPdNLzExUb1791ZQUJDmzp2r2NhYSVJmZqb69eun5ORkLVy4UCEhIVaWDIsxJxRvzAkoCg6HQwEBf+x0lZeXp0cffdQZxAp2TZw2bZp69+5tXaG4LOfOG6mpqbrrrrt0/PhxLVy4UHFxcZLye/7cc89p7ty5Wrp0qcqVK2dlyV6FY8IgKf9TjIMHD6pUqVKqUKGCrrjiCufkmZeXp5CQEH355Zfq2LGjXnjhBdntdi1fvlzz5s3T9ddfr5iYGKufAlxw7h/SBZNn/fr19b///U+HDx9WdHS0pPzdz0qWLKlrr71W27ZtY5cRP8Sc4B+YE+BOhw8f1s6dOxUUFKTq1as7x4+U/8d4UFCQJk6cqMGDB2vWrFlyOBzau3evpk6dqhYtWjj/cId3y87OVmhoqKQ/5o2oqCjNmTNH69atcx476nA4FBQUpJiYGGVnZxf6IA+SDPxeUlKSqVGjhrn66qtNbGysadSokVm7dm2hdXJzc40xxmRnZ5s77rjDBAcHm7CwMLNx40YrSsZl2LFjh+nevXuhnjkcDmOMMXa73djt9vMe06dPH9O7d29n/+EfmBP8A3MC3CkpKcnExcWZ6tWrm5iYGBMdHW1mz55tsrOznesUjJvc3FzzyCOPmNDQUBMREWE2bdpkVdm4RD///LO56aabzPLly40x+XNGwbxxMQMGDDCdO3c2mZmZHqjQd3BiDj935MgRtWvXTh07dtTChQv15ptv6pprrlHz5s01Y8YM53pBQUGy2+0KCQlRXFycwsPD9eOPP3LGGx+xd+9e3XbbbVq4cKGee+45JSYmSpLzhAoBAQGFdhlJTU3VqFGjNH/+fI0YMUJBQWw09xfMCf6BOQHudOzYMXXt2lX33HOPVq5cqXnz5unee+9Vt27dNGHCBJ0+fVrSH/NGUFCQAgICVKpUKa1Zs0YNGjSw+BnAFfv371f79u21fft2DR8+XN99991fHs/322+/6amnntJnn32mZ555RiVKlPBgtT7A6hQIayUmJpratWubffv2Oe87e/asefzxx01ISIiZP3++McY4PxGdNGmSsdlsfGrlQ86ePWt69+5tunTpYiZNmmRuvfVW065du4v2cPHixaZXr14mNjaWPvsh5oTijzkB7rZ3715z7bXXmg0bNhS6f8KECcZms5k333zTGPPHvPH+++8zb/iYrKwsM2jQINOpUyfz6aefmrvvvtvUrVvXrFixwhhjztsa9v3335uHHnrIxMXFmcTERAsq9n6EMD+3YsUKY7PZzN69e40xf0yQDofDDBw40ERERJhdu3Y51z9+/LjZs2ePJbXi8s2YMcO89957xhhjPv/887/8o+vw4cNmypQpzjEB/8Kc4B+YE+BOmzdvNiEhIWb9+vXGGGNycnKcy8aPH2+CgoLOC2jnftAD37Bw4ULnvLF27VrTtWvXQkHsXKmpqWbevHnm119/9XSZPoOzI/o5u92u//f//p8qVaqkt99+W1FRUc6D7w8dOqTu3bvr1ltv1ZgxY5y7qMD3zZ49W++++65KlSqlZ599VvXr11d2drZOnDihmJiY885oBf/BnOCfmBPwTxWcLXXevHmqUKGC8vLyFBgYKElq3769oqKiNGXKFBljOLNmMbF69WpNnDhRO3bs0MSJE3XzzTcrOztbu3fv1nXXXWd1eV6PGdXPBQYGqlu3btq/f78mTpyo9PR05xvtlVdeqdKlS2vHjh2y2Wy8ARcDdrtdktSlSxf169dPZ8+e1dixY7V+/XoNHTpUjRs3VnZ2Ntds8WPMCf6FOQHu0q9fPwUHB2vEiBE6fvy4goKCnGfOi46O1vHjxxUcHEwAKwYKzo564403avDgwapZs6YGDx6sZcuWacSIEbr11ludxwHi4jiy1o8VTI79+/fXnj17NHfuXGVmZurf//63IiIiJElly5bVFVdcIbvdroCAAN6IfVRBrwMDA52npO7atatsNpvee+89tWnTRna7XV9//bXztLPwP8wJ/oM5Ae7Wpk0b7dmzRx999JH69++vt956SxUrVpQkBQQEqEyZMsrJyVFwcDDzho8qmDcCAgKc88aNN94oSXrzzTfVunVrhYeH6+uvv1Z4eLjF1Xo/dkf0Y3a7XYGBgc7dTMaNG6cFCxbo1KlTat++vQ4ePKj58+frhx9+YLOyDyvoc1pamiIjIyUVvsDirbfeqk2bNun7779X7dq1rSwVFmNO8A/MCXCngvGUlZWlEiVK6H//+5+mTJmibdu26Y477lBaWpq+/fZbrVmzRnXq1LG6XFymgj6npqYqKipKUuF5o127dlq1apVWrVrF+4OL2JfED5w5c0aZmZmF7it4Mf3666+qU6eOVqxYoTFjxuill15Sq1attGXLFoWGhmrt2rW8mHzE3/W5efPmmj9/vqT801Dn5eXpiSee0Pfff68VK1bwx5YfOXjwoHbt2lXoPuaE4ufv+sycgEuxd+9erV69utB9546nuLg4ffHFF+rRo4c++OADDRkyRJJ01VVX6ccffySA+Yi/63Pt2rX1ySefSMqfN+x2u8aPH69vv/1Wy5cv5/3hUnj+XCDwpJ07d5p69eqZadOmmbNnzxZatn//fnPllVeafv36nXfhTYfDccELdcI7udrnP59CdsaMGWbz5s2eLBUW27Rpk6lQoYKZPXv2ecuYE4oPV/vMnABXJCUlmUqVKpkHH3zQpKSkFFr266+/mpiYGPPII49wEW8f52qf/zxvLFq0yPz888+eLLVYYHfEYm7kyJF66aWXFBMTo1deeUWdOnVSaGiojDHq06ePgoKC9N///te5Odmcs2kZvoM+wxVJSUm68cYb9fDDD+v1118vtMwYowceeEBBQUF67733GCs+jD7Dnfbt26dmzZqpR48eevHFF887Ic8zzzyj1NRUvfHGG4wnH3Y5fcY/Qwgr5pYsWaKVK1cqKytLb731lqZMmaL77rtPNpuNSbIYoc/4Ozt27FCjRo00ZMgQPf/888rLy9OaNWt08uRJlStXTjfeeKPy8vIUFMT5mnwZfYa7ffTRR5o3b55mz56tvLw8TZgwQbt27dKVV16pdu3aqVGjRpIIXr6OPnses7AfmDt3rrZs2aJTp06pX79+KlOmjObNm6e6detq0KBBVpcHN6HPuJicnBw99dRTKl26tDp27ChJ6tSpkw4cOKDDhw/r5MmTevjhh/XMM8+oXLly1haLy0afURQ2bdqk7OxsSVLLli2Vm5urypUr69NPP9WSJUvUu3dvPfzww/xh7uPos+dxYo5irmnTpoqKilJWVpamTJmiBx98UHfddZdmzZqlpk2bWl0e3IQ+46+EhIRo9OjRql+/vsaOHatatWopNzdX77//vtatW6fPP/9c7733nt544w2rS8U/QJ9RFOrWravQ0FDNmDFDwcHB+uKLLzRjxgwtX75c1atX1+zZs5Wammp1mfiH6LPnEcKKuYiICGVkZGjNmjWSpLNnz6pEiRLKysrS/v37lZWVZXGFcAf6jL/TuHFjPf/880pPT1flypX1zjvvqGHDhoqLi1O7du306quvavLkyUpOThZ7qfsu+gx3q1WrlubPn69XX31VZcqUcV77KyYmRiNHjtQ333yjxMREi6vEP0WfPY/dEYuJgwcPavv27Tp27Jhuu+02lSlTRiEhIbLb7apRo4bsdrsGDx6shQsXauvWrXrllVd09913a+bMmerSpYvV5cNF9BmuOnestGzZUpGRkWrcuLEmT56snTt3KjY2VtIf+/fbbDZVqlRJZcuWZXcTH0Kf4U5/fo8JDw9XQkKCXnvtNQ0ePFjGGO3bt09Vq1aVJFWoUEFNmzZVmTJlrC0cl4Q+ewkPnokRRSQpKclUrFjRNGzY0ISEhJjrrrvOjBgxwpw4ccIYY8zzzz9vbDabqVSpklm/fr3zcUOGDDHbt2+3qmxcIvoMV11orAwfPtw5VnJycs57zGOPPWa6dOliMjIyPF0uLhN9hjtdaDw9/vjjJjU11RhjzLhx44zNZjN9+/Y1q1atMikpKWb06NGmatWqJjk52eLq4Sr67D0IYT7u1KlTpmHDhs433szMTDNy5EjTrFkz0759e3Py5EmTlJRkevfubRITE40xxuTl5VlbNC4ZfYar/mqsdOjQwfkHeoG9e/eaMWPGmDJlypitW7daVDUuFX2GO/3VeOrYsaPzD/T333/fVKpUyURHR5v4+HhTpUoVs2nTJourh6vos3chhPm4ffv2mWrVqpkVK1Y478vOzjbvv/++ueGGG0zPnj1NdnY2F1D0cfQZrvqrsZKQkGDuu+8+k56ebowxZsuWLaZ9+/bmqquucoZ3+Ab6DHf6u/eY++67z6SlpRlj8gP96tWrzfLly82hQ4esKhmXgT57F07M4eNKly6tUqVKacuWLZLy9/sPCQlRr1691LNnT/3000+aOXOmgoKCOAjbh9FnuOqvxsr999+v7du368svv5QkXX311Xrsscf07bffqn79+tYVjUtGn+FOf/cec+54qlq1qpo1a6ZbbrlFMTExFlaNS0WfvQsXa/Zxubm5uvfee3X48GFNnz5dcXFxhZa3bt1awcHBmj9/vkUVwh3oM1zlylgJCgrSggULLKoQ7kCf4U68x/gH+uxd2BLmw4wxCg4O1ttvv609e/Zo8ODBSklJKbQlpF27djp+/DinKPdh9BmucnWsnDhxgrHiw+gz3In3GP9An70PIcyH2Ww25eTkqEKFClq8eLF+/PFH3X///dqwYYPsdrskafPmzSpbtqwCAmi1r6LPcBVjxT/QZ7gT48k/0Gfvw+6IPsxutyswMFAnTpxQTk6OMjMz1aZNG5UuXVp5eXmqVq2ali1bplWrVqlu3bpWl4vLRJ/hKsaKf6DPcCfGk3+gz96HqOujCl5M+/fvV926dbVs2TJVq1ZN69ev15AhQ3Tbbbfp+uuv1/r163kx+TD6DFcxVvwDfYY7MZ78A332TmwJ83JHjx5VWlqaatSocd6y3377TXXq1FHXrl01efJkGWPYhOyj6DNcxVjxD/QZ7sR48g/02bfwv+/Ftm/friZNmmjMmDHatm3becs3bNigvn37avLkybLZbLyYfBR9hqsYK/6BPsOdGE/+gT77HraEeank5GR17dpVGRkZCg0NVZ06dTRkyBDVrl3buU5ubq6Cg4MtrBL/FH2Gqxgr/oE+w50YT/6BPvsmYrCX2rFjh8LDw/Xhhx9qwIABSkxM1H/+8x9t3brVuQ4vJt9Hn+Eqxop/oM9wJ8aTf6DPvoktYV4qKytLiYmJSkhIkCR98MEHeuutt9SgQQM99thjqlOnjqT86z7YbDY5HA42Lfsg+gxXMVb8A32GOzGe/AN99k10wEuVKFFCTZs2df67T58+Gjx4sBITE/XGG284P90YN26cfvrpJ15MPoo+w1WMFf9An+FOjCf/QJ99E1vCvERycrI2bdqknJwcxcXFqVGjRpLyP7U49ww2H374oSZOnKiGDRsqPT1ds2fP1pYtWxQfH29l+XARfYarGCv+gT7DnRhP/oE+FxMGlvvpp59MtWrVTJMmTUy5cuVM48aNzaxZswqtY7fbnbenTp1qgoODTWRkpElMTPRwtbhc9BmuYqz4B/oMd2I8+Qf6XHywPdJie/bs0R133KEuXbpoyZIlWrx4sa677jotWrRIdrtd5vcNlQEBATLGyG63KykpSaVLl9bq1atVv359a58AXEKf4SrGin+gz3AnxpN/oM/FjDXZD8YYk52dbYYNG2buvvtuk52d7bx/6tSppmzZsub48ePnPWbdunXGZrOZ9evXe7JU/AP0Ga5irPgH+gx3Yjz5B/pc/ARZHQL9mcPhUGxsrGrVqqWQkBDnWWuaNWum0qVLKzc397zHXH/99UpNTVWZMmU8XzAuC32Gqxgr/oE+w50YT/6BPhc/hDALlShRQh07dlTVqlUL3V+mTBkFBwcXekElJiaqQYMGkqTIyEiP1ol/hj7DVYwV/0Cf4U6MJ/9An4sfjgnzsMOHD2vdunVavHixHA6H88Vkt9tls9kkSWlpaTp58qTzMWPHjtWtt96qEydOOD/5gHejz3AVY8U/0Ge4E+PJP9DnYs6avSD9U1JSkomLizM1atQwkZGRpmbNmmb69OnmxIkTxhhjHA6HMcaYnTt3mvLly5vU1FQzbtw4U7JkSbNhwwYrS8cloM9wFWPFP9BnuBPjyT/Q5+KPEOYhKSkppmbNmmbUqFFmz5495tChQ6Zbt26mVq1a5umnnzYpKSnOdY8ePWoaNGhgunXrZkJCQngx+RD6DFcxVvwDfYY7MZ78A332D4QwD9m2bZu56qqrzntxPPnkk6ZOnTrm5ZdfNhkZGcYYY37++Wdjs9lMyZIluaaDj6HPcBVjxT/QZ7gT48k/0Gf/wDFhHpKbm6u8vDydPXtWkpSZmSlJevHFF9WiRQu988472r17tyTpiiuu0IABA7Rp0yau6eBj6DNcxVjxD/QZ7sR48g/02T/YjPn9ym4ock2aNFHp0qX17bffSpKys7MVGhoqKf80otWrV9enn34qScrKylKJEiUsqxWXjz7DVYwV/0Cf4U6MJ/9An4s/toQVkYyMDJ0+fVrp6enO+yZPnqxt27ape/fukqTQ0FDl5eVJkpo3b66MjAznuryYfAN9hqsYK/6BPsOdGE/+gT77J0JYEfj555/VqVMn3XzzzapVq5Y++eQTSVKtWrX0xhtvaOnSperatatyc3MVEJDfgpSUFIWFhSkvL09snPQN9BmuYqz4B/oMd2I8+Qf67L+4WLOb/fzzz2revLl69uypxo0ba+PGjerTp4/i4+PVoEEDtW/fXmFhYRowYIDq1q2rmjVrKiQkRAsWLNAPP/ygoCBa4gvoM1zFWPEP9BnuxHjyD/TZv3FMmBulpqbq3nvvVc2aNfXGG28472/RooXq1KmjiRMnOu87ffq0nnvuOaWmpqpEiRLq37+/4uPjrSgbl4g+w1WMFf9An+FOjCf/QJ9BhHaj3NxcnTp1Sl26dJEkORwOBQQEqGrVqkpNTZUkmfzLAig8PFwvvfRSofXgG+gzXMVY8Q/0Ge7EePIP9Bl00Y0qVqyojz/+WP/6178kSXa7XZJ05ZVXOl8wNptNAQEBhQ6+tNlsni8Wl40+w1WMFf9An+FOjCf/QJ9BCHOza665RlL+JxXBwcGS8j/JSElJca4zfvx4TZkyxXmWG15Qvoc+w1WMFf9An+FOjCf/QJ/9G7sjFpGAgAAZY5wvloJPNcaOHavnnntOiYmJHFBZDNBnuIqx4h/oM9yJ8eQf6LN/YktYESo450lQUJAqV66sV199VS+//LI2bNigevXqWVwd3IU+w1WMFf9An+FOjCf/QJ/9D7G6CBV8khEcHKz//ve/ioiI0KpVq9SwYUOLK4M70We4irHiH+gz3Inx5B/os/9hS5gHtG7dWpK0Zs0aNW7c2OJqUFToM1zFWPEP9BnuxHjyD/TZf3CdMA/JyMhQWFiY1WWgiNFnuIqx4h/oM9yJ8eQf6LN/IIQBAAAAgAexOyIAAAAAeBAhDAAAAAA8iBAGAAAAAB5ECAMAAAAADyKEAQAAAIAHEcIAAAAAwIOCrC4AAABPsdlshf4dFBSkyMhIVapUSY0aNVK7du3UoUMHBQXx9ggAKDpcJwwA4DcKQlivXr0kSQ6HQ2lpadq1a5d27twpY4yqV6+uTz75RE2aNPnHv2/atGnq06ePnn76aT3zzDP/+OcBAIoHPuoDAPidadOmnXffnj17NGrUKM2cOVMtWrTQ6tWrVb9+fY/XBgAo/jgmDAAASVdffbU+++wz9e3bV2fPntUDDzxgdUkAgGKKEAYAwDlee+01hYWFKTExUatWrSq0bMGCBXrggQdUq1YtRUREKCwsTPXq1dMLL7yg7OzsQuvecsst6tOnjyTp//7v/2Sz2Zxff94St337dvXu3VuVK1dWaGioKlasqHvuuUfbtm0r0ucKALAGuyMCAHCOyMhItWnTRrNnz9by5ct10003OZf17dtXmZmZql27turWrau0tDStW7dO//73v7Vs2TItWbJEgYGBkqTbb79deXl5Wr16terVq1do18bq1as7b3/55Ze65557lJ2drfr166tp06Y6ePCgZs6cqa+++kqLFi1S8+bNPfb8AQBFjxAGAMCf1K9fX7Nnz9b27dsL3T958mS1atVKJUuWdN53+vRpde/eXfPnz9cnn3yinj17SpKeeuopRUdHa/Xq1erYseMFT8yxf/9+3X///QoODtb8+fPVsmVL57LFixerffv2uv/++7V7926FhIQUzZMFAHgcuyMCAPAn5cqVkySdPHmy0P0dOnQoFMAkKTw8XBMmTJAkzZ0795J+z3/+8x9lZGRo/PjxhQKYlL8lrX///jp48KAWLFhwqU8BAODF2BIGAMCfFFy95c/XFZOkX375RQsXLtTu3buVkZEhh8PhXP+XX365pN+zZMkSSVKnTp0uuPxf//qXJk6cqHXr1umuu+66pJ8NAPBehDAAAP7k+PHjkqSoqCjnfcYYPf7445owYYIudonN06dPX9Lv2b9/vyTpyiuvdKkeAEDxQAgDAOBPEhMTJUnx8fHO+z777DO9/vrrqly5siZMmKCEhASVL19ewcHBysnJUWho6EXD2cU4HA5Jf1w8+mJuuOGGS3wGAABvRggDAOAcaWlp+vrrryVJLVq0cN4/Z84cSdI777yjtm3bFnrM3r17L+t3xcbGas+ePXrttddUtmzZy6wYAOBrODEHAADnGD58uDIyMnT99dcrISHBeX/BSTpiY2PPe8zMmTMv+LMKzmiYl5d3weW33XabpD8CHgDAPxDCAABQ/tasbt26aerUqQoLC9PUqVMLLa9Ro4Yk6b333iu02+H333+vV1555YI/MyYmRpK0c+fOCy4fPny4SpYsqccff1xffPHFecuzs7M1e/Zs/fbbb5f1nAAA3slmLnUHdgAAfFTB2Q4LjsFyOBxKT0/Xrl27tGPHDhljdM0112j69Olq3Lhxocfu2rVLDRs2VEZGhuLj41W3bl0dOnRIq1at0vDhw/Xqq68qLi7OebINScrKylJcXJxSUlJ08803q1q1agoICNADDzygZs2aSco/rX337t119uxZVa9eXbVq1VJYWJgOHTqkTZs2KSMjQ4mJiYUu9gwA8G2EMACA3/jzKeeDgoIUERGhmJgYNWrUSB06dFD79u0VGBh4wcfv2LFDTzzxhH788UedOXNG1157rfr376+HHnpINpvtvBAmSRs2bNCoUaO0bt06paenyxijDz74QL1793aus2fPHr3++utaunSpDh48qODgYMXExKhBgwbq1KmTOnTowMWaAaAYIYQBAAAAgAdxTBgAAAAAeBAhDAAAAAA8iBAGAAAAAB5ECAMAAAAADyKEAQAAAIAHEcIAAAAAwIMIYQAAAADgQYQwAAAAAPAgQhgAAAAAeBAhDAAAAAA8iBAGAAAAAB5ECAMAAAAADyKEAQAAAIAH/X/pj+sHYNA47wAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        " <h1> <p align = \"center\"> ------------ THANK YOU --------------- </h1>\n",
        "\n"
      ],
      "metadata": {
        "id": "h5zLWxFOJ1SE"
      }
    }
  ]
}