machine_learning/ECG_Model.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "M5ptZVaN5hZJ"
      },
      "source": [
        "# Normal vs Heart Attack Classification Model using ECGs"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JXCALUfH5oqw"
      },
      "source": [
        "## Get the Data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PDmJrPB36kRq",
        "outputId": "b172fbbc-55b7-4f5f-85e1-43ddedcee6db"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: tensorflow in /usr/local/lib/python3.10/dist-packages (2.15.0)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.23.5)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (1.11.4)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (1.2.2)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (1.5.3)\n",
            "Collecting wfdb\n",
            "  Downloading wfdb-4.1.2-py3-none-any.whl (159 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m160.0/160.0 kB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=23.5.26 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (23.5.26)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.5.4)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.9.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (16.0.6)\n",
            "Requirement already satisfied: ml-dtypes~=0.2.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.3.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from tensorflow) (23.2)\n",
            "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.20.3)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from tensorflow) (67.7.2)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.16.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (4.5.0)\n",
            "Requirement already satisfied: wrapt<1.15,>=1.11.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.14.1)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.35.0)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.60.0)\n",
            "Requirement already satisfied: tensorboard<2.16,>=2.15 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.15.1)\n",
            "Requirement already satisfied: tensorflow-estimator<2.16,>=2.15.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.15.0)\n",
            "Requirement already satisfied: keras<2.16,>=2.15.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.15.0)\n",
            "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.3.2)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (3.2.0)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.3.post1)\n",
            "Requirement already satisfied: SoundFile>=0.10.0 in /usr/local/lib/python3.10/dist-packages (from wfdb) (0.12.1)\n",
            "Requirement already satisfied: matplotlib>=3.2.2 in /usr/local/lib/python3.10/dist-packages (from wfdb) (3.7.1)\n",
            "Requirement already satisfied: requests>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from wfdb) (2.31.0)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from astunparse>=1.6.0->tensorflow) (0.42.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.2.2->wfdb) (1.2.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.2.2->wfdb) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.2.2->wfdb) (4.47.2)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.2.2->wfdb) (1.4.5)\n",
            "Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.2.2->wfdb) (9.4.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.2.2->wfdb) (3.1.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.8.1->wfdb) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.8.1->wfdb) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.8.1->wfdb) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.8.1->wfdb) (2023.11.17)\n",
            "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/dist-packages (from SoundFile>=0.10.0->wfdb) (1.16.0)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (2.17.3)\n",
            "Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (1.2.0)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (3.5.2)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (3.0.1)\n",
            "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0->SoundFile>=0.10.0->wfdb) (2.21)\n",
            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (5.3.2)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (0.3.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow) (1.3.1)\n",
            "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/dist-packages (from werkzeug>=1.0.1->tensorboard<2.16,>=2.15->tensorflow) (2.1.3)\n",
            "Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (0.5.1)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow) (3.2.2)\n",
            "Installing collected packages: wfdb\n",
            "Successfully installed wfdb-4.1.2\n"
          ]
        }
      ],
      "source": [
        "# Install Python dependencies\n",
        "!pip install tensorflow numpy scipy scikit-learn pandas wfdb"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 33,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BHafT_wL5sOs",
        "outputId": "60cab02e-cf48-479c-e4a9-50ef00d7dc29"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Drive already mounted at /content/drive/; to attempt to forcibly remount, call drive.mount(\"/content/drive/\", force_remount=True).\n"
          ]
        }
      ],
      "source": [
        "# Dataset Originally from here: https://www.physionet.org/content/ptb-xl/1.0.3/records500/21000/\n",
        "# The dataset is saved in a google drive folder, and was preprocessed to only contain the second\n",
        "# lead sampled at 100Hz.\n",
        "import os\n",
        "import numpy as np\n",
        "from google.colab import drive\n",
        "\n",
        "# Mount google drive\n",
        "MOUNT_DIR = \"/content/drive\"\n",
        "drive.mount('/content/drive/')\n",
        "\n",
        "# Load the saved data\n",
        "DATA_PATH = os.path.join(MOUNT_DIR, \"MyDrive\", \"datasets\", \"ecg.npz\")\n",
        "data = np.load(DATA_PATH)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "l0sZgkly6aCP"
      },
      "source": [
        "## Preprocess the Dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 34,
      "metadata": {
        "id": "XSptpfsE7YFk"
      },
      "outputs": [],
      "source": [
        "%matplotlib inline\n",
        "import matplotlib.pyplot as plt\n",
        "from scipy import stats\n",
        "\n",
        "def compute_p2p_stats(signals):\n",
        "  p2p_voltages = np.max(signals, axis=1) - np.min(signals, axis=1)\n",
        "  mean = np.mean(p2p_voltages)\n",
        "  median = np.median(p2p_voltages)\n",
        "  std = np.std(p2p_voltages)\n",
        "  return p2p_voltages, mean, median, std\n",
        "\n",
        "def plot_histogram(p2p, mean, median, std, num_stds, title):\n",
        "  plt.clf()\n",
        "  plt.hist(p2p, bins=20)\n",
        "  plt.axvline(x=mean, c=\"r\", label=\"mean\")\n",
        "  plt.axvline(x=median, c=\"k\", label=\"median\")\n",
        "  plt.axvline(x=median+(std*num_stds), c=\"b\", label=f\"+/-{num_stds} Standard Deviations\")\n",
        "  plt.axvline(x=median-(std*num_stds), c=\"b\")\n",
        "  plt.title(title)\n",
        "  plt.xlabel(\"p2p voltages\")\n",
        "  plt.legend()\n",
        "  plt.show()\n",
        "\n",
        "\n",
        "norm, mi = data[\"arr_0\"], data[\"arr_1\"]\n",
        "\n",
        "p2p_norm, mean_norm, median_norm, std_norm = compute_p2p_stats(norm)\n",
        "p2p_mi, mean_mi, median_mi, std_mi = compute_p2p_stats(mi)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 35,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "QhsgANNG9APG",
        "outputId": "435c9216-c8ee-45b9-bf8a-e80332bdfda4"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "nstds_norm = 1.\n",
        "plot_histogram(p2p_norm, mean_norm, median_norm, std_norm, nstds_norm, \"Normal ECG Peak-to-Peak Voltages\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 36,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "CvFNEPrs8_2K",
        "outputId": "89f9ca6f-4259-4780-c855-89942aebd329"
      },
      "outputs": [
        {
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjAAAAHHCAYAAAChjmJTAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAABVnElEQVR4nO3deVgVZf8G8PsAcljPQZA1EVBSQAERC8kNlUBEyiUXJCRzeVX0DTE1y1xLXMI109QUM3BNszRBxF1xQzG3SA3DVCAXQBYBYX5/+GNej4CCQofB+3Ndc12cmWee+c4AcjvzzIxMEAQBRERERBKioe4CiIiIiKqLAYaIiIgkhwGGiIiIJIcBhoiIiCSHAYaIiIgkhwGGiIiIJIcBhoiIiCSHAYaIiIgkhwGGiIiIJIcBhohe2vXr1yGTyfDVV1+pu5Q6w9bWFj179lR3GQCA6dOnQyaTqbsMohrFAEP1SlRUFGQyGWQyGY4cOVJuuSAIsLa2hkwmK/fHRSaTYcyYMc/dhq2trbiNp6fu3buXa5+cnIz3338f1tbWkMvlMDY2hre3N9auXYuSkhKVtoWFhVi6dCk6dOiAhg0bQltbG1ZWVnjnnXewYcOGcu2rUp+ZmRk6duyI7du3P3dddTl27BimT5+OrKysGu/7gw8+UDkeCoUCrq6uiIyMRGFhYY1v72VkZmZCS0sL77//fqVtHjx4AF1dXfTp0+eltjV79mz89NNPL9UHkTppqbsAotqgo6ODmJgYdOjQQWX+wYMH8ffff0Mul79U/61bt8b48ePLzbeyslL5vHr1aowcORLm5uYIDg7G66+/jgcPHiAhIQFDhw7F7du38emnnwIA/vnnH/j5+SEpKQm+vr6YMmUKjI2NkZ6ejr1792LQoEG4evUqPv/882rVd+vWLXz77bfo06cPli9fjpEjR77UvteGY8eOYcaMGfjggw9gZGRU4/3L5XKsXr0aAJCVlYUff/wRH3/8MU6dOoWNGzfW+PZelJmZGd5++23s2LED+fn50NPTK9dm27ZtePjw4TNDTlXMnj0b7733Hnr16vVS/RCpCwMM1Us9evTAli1bsGTJEmhp/e/HPCYmBu7u7rhz585L9f/aa6899w/I8ePHMXLkSHh6euLXX3+FoaGhuCwsLAynT5/GhQsXxHnBwcE4e/Ysfvzxx3L/u548eTJOnz6NlJSUF6pv8ODBsLe3x8KFC+tkgKltT5/VGD16NDw8PLBp0yYsWLCgXPBUp6CgIMTGxuLnn3/GwIEDyy2PiYmBUqmEv7+/Gqojqjt4CYnqpcDAQNy9exfx8fHivKKiImzduhWDBg36V2qYMWMGZDIZoqOjVcJLmbZt2+KDDz4AACQmJiIuLg4jRoyo9NJA27ZtERQU9EK1WFhYwNHREampqeK8mzdv4sMPP4S5uTnkcjlatmyJNWvWqKxXVFSEqVOnwt3dHUqlEvr6+ujYsSP279//3G0KgoARI0ZAW1sb27Ztq7Td9OnTMWHCBACAnZ2deKnn+vXrAIBHjx5h1qxZaNasGeRyOWxtbfHpp5++1OUfDQ0NeHl5AYC4ncLCQkybNg329vaQy+WwtrbGxIkTy21n7dq16Nq1K8zMzCCXy+Hk5ITly5dXabvr1q2DlpaWuL8V6d27N/T19RETE1NuWWZmJhISEvDee++JZxG3bNkCd3d36OrqolGjRnj//fdx8+bNZ9Yhk8mQl5eHdevWice77Gfxr7/+wujRo9GiRQvo6urCxMQE/fr1E4/Tk3777Td07twZurq6aNy4Mb744gusXbtW5ftXZvfu3ejYsSP09fVhaGgIf39/XLx4UaVNeno6hgwZgsaNG0Mul8PS0hLvvvtuhdsm4hkYqpdsbW3h6emJDRs2wM/PD8Djf0Czs7MxcOBALFmy5KX6Ly4urvAsjr6+PnR1dZGfn4+EhAR06tQJTZo0eW5/v/zyCwC89GWByhQXF+PGjRswMTEBAGRkZKBdu3biuB9TU1Ps3r0bQ4cORU5ODsLCwgAAOTk5WL16NQIDAzF8+HA8ePAA3333HXx9fXHy5Em0bt26wu2VlJTgww8/xKZNm7B9+/Znni3o06cP/vjjD2zYsAELFy5Eo0aNAACmpqYAgGHDhmHdunV47733MH78eJw4cQIRERG4fPnyS43ruXbtGgDAxMQEpaWleOedd3DkyBGMGDECjo6OOH/+PBYuXIg//vhDZazI8uXL0bJlS7zzzjvQ0tLCL7/8gtGjR6O0tBShoaGVbm/lypUYOXIkPv30U3zxxReVttPX18e7776LrVu34t69ezA2NhaXbdq0CSUlJWKQjYqKwpAhQ/DGG28gIiICGRkZWLx4MY4ePYqzZ89Wejlu/fr1GDZsGN58802MGDECANCsWTMAwKlTp3Ds2DEMHDgQjRs3xvXr17F8+XJ4eXnh0qVL4mWtmzdvokuXLpDJZJg8eTL09fWxevXqCi/Prl+/HiEhIfD19cXcuXORn5+P5cuXo0OHDjh79ixsbW0BAH379sXFixcxduxY2NraIjMzE/Hx8UhLSxPbEIkEonpk7dq1AgDh1KlTwtdffy0YGhoK+fn5giAIQr9+/YQuXboIgiAINjY2gr+/v8q6AITQ0NDnbsPGxkYAUOEUEREhCIIgnDt3TgAgfPTRR1Wqu3fv3gIAISsrS2V+QUGB8M8//4jT/fv3q1Sfj4+PuM65c+eEgQMHCgCEsWPHCoIgCEOHDhUsLS2FO3fuqKw7cOBAQalUisfs0aNHQmFhoUqb+/fvC+bm5sKHH34ozktNTRUACPPnzxeKi4uFAQMGCLq6ukJcXFyV9n/+/PkCACE1NVVlfnJysgBAGDZsmMr8jz/+WAAg7Nu377l9h4SECPr6+uLxuHr1qjB79mxBJpMJLi4ugiAIwvr16wUNDQ3h8OHDKuuuWLFCACAcPXpUnFd2bJ7k6+srNG3aVGXekz9jixcvFmQymTBr1qzn1isIgrBr1y4BgPDtt9+qzG/Xrp3w2muvCSUlJUJRUZFgZmYmtGrVSigoKBDb7Ny5UwAgTJ06VZw3bdo04el/7vX19YWQkJBy265o/xITEwUAwvfffy/OGzt2rCCTyYSzZ8+K8+7evSsYGxurfC8fPHggGBkZCcOHD1fpMz09XVAqleL8+/fviz9DRFXBS0hUb/Xv3x8FBQXYuXMnHjx4gJ07d9bY5SMPDw/Ex8eXmwIDAwE8PnMBoMJLRxUpa29gYKAyf8WKFTA1NRWnpwclV2bPnj3iOq6urtiyZQuCg4Mxd+5cCIKAH3/8EQEBARAEAXfu3BEnX19fZGdn48yZMwAATU1NaGtrAwBKS0tx7949PHr0CG3bthXbPKmoqAj9+vXDzp078euvv8LHx6dK9Vbm119/BQCEh4erzC8boLxr164q9ZOXlyceD3t7e3z66afw9PQUz+Bs2bIFjo6OcHBwUDkeXbt2BQCVS2a6urri19nZ2bhz5w46d+6MP//8E9nZ2eW2PW/ePHz00UeYO3cupkyZUqV6fXx8YGpqqnIZKTU1FcePH0dgYCA0NDRw+vRpZGZmYvTo0dDR0RHb+fv7w8HBocrH5mlP7l9xcTHu3r0Le3t7GBkZqXzPY2Nj4enpqXIWztjYuNxlzvj4eGRlZSEwMFDl2GpqasLDw0M8trq6utDW1saBAwdw//79F6qdXi28hET1lqmpKby9vRETE4P8/HyUlJTgvffeq5G+GzVqBG9v70qXKxQKAI9vea2KsqCTm5sLpVIpzu/bty9atWoF4PEf7arcRg08DlhffPEFZDIZ9PT04OjoKF5OyMzMRFZWFlauXImVK1dWuH5mZqb49bp16xAZGYnff/8dxcXF4nw7O7ty60VERCA3Nxe7d+8Wx5iUKSkpwT///KMyz9jYWAxIFfnrr7+goaEBe3t7lfkWFhYwMjLCX3/9BQAoKCgoFx4sLCzEr3V0dMTLdHK5HHZ2dmjcuLG4/MqVK7h8+bJ42eppTx6Po0ePYtq0aUhMTER+fr5Ku+zsbJXv38GDB7Fr1y5MmjTpmeNenqalpYUBAwbgm2++wc2bN/Haa6+JYaYsIJTte4sWLcqt7+DgUOFjBKqioKAAERERWLt2LW7evAlBEFT2r8xff/0FT0/Pcus//b26cuUKAIhh8GllvytyuRxz587F+PHjYW5ujnbt2qFnz54YPHiwyveSqAwDDNVrgwYNwvDhw5Geng4/P79auUW3Ivb29tDS0sL58+er1N7BwQEAcOHCBbRv316cb21tDWtrawBAw4YNq3z31LMCVmlpKYDH421CQkIqbOPi4gIA+OGHH/DBBx+gV69emDBhAszMzKCpqYmIiAhxDMmTfH19ERsbi3nz5sHLy0vlzMCNGzfKhZ79+/eXCzoVed5D2DZt2oQhQ4aozHvyD6+mpuYzA2dpaSmcnZ2xYMGCCpeXfQ+uXbuGbt26wcHBAQsWLIC1tTW0tbXx66+/YuHCheKxLdOyZUtkZWVh/fr1+M9//lNh6KvM+++/j6+//hobNmzAxx9/jA0bNsDJyanScUc1ZezYsVi7di3CwsLg6ekJpVIJmUyGgQMHltu/qihbZ/369RUGkSfvEgwLC0NAQAB++uknxMXF4fPPP0dERAT27dsHNze3F98pqpcYYKhe6927N/7zn//g+PHj2LRp07+2XT09PXTt2hX79u3DjRs3xD+AlenZsyfmzJmD6OholQBTG0xNTWFoaIiSkpJn/lEHgK1bt6Jp06bYtm2bSoiYNm1ahe3btWuHkSNHomfPnujXrx+2b98u/oGysLBQuSsMAFxdXQFUHlBsbGxQWlqKK1euwNHRUZyfkZGBrKws2NjYAHgcnJ7uuzqaNWuGc+fOoVu3bs8MS7/88gsKCwvx888/qwzOruyurEaNGmHr1q3o0KEDunXrhiNHjlT5lm0PDw80a9YMMTExePvtt3Hx4kV8+eWX4vKyfU9JSSl3diMlJUVcXpnK9nPr1q0ICQlBZGSkOO/hw4flHjJoY2ODq1evllv/6Xllg4PNzMye+/NW1n78+PEYP348rly5gtatWyMyMhI//PDDc9elVwvHwFC9ZmBggOXLl2P69OkICAj4V7c9bdo0CIKA4OBg5ObmlluelJSEdevWAQDat2+Pt99+GytXrsSOHTsq7O/JMwovQ1NTE3379sWPP/6o8hyaMk9e5tHU1Cy37RMnTiAxMbHS/r29vbFx40bExsYiODhY/B+4jo4OvL29VaaGDRsCeHznDYByfyR79OgBAFi0aJHK/LIzJWV3N1laWpbruzr69++PmzdvYtWqVeWWFRQUIC8vD0DFxyM7Oxtr166ttO/GjRtj7969KCgowNtvv427d+9Wua6goCCcPXsW06ZNg0wmUxnD1bZtW5iZmWHFihUqt3rv3r0bly9ffu5zYvT19St88rGmpma5n7WlS5eWu3zp6+uLxMREJCcni/Pu3buH6Ojocu0UCgVmz56tcgmyTNnPW35+Ph4+fKiyrFmzZjA0NKxzT0ymuoFnYKjeq+wyycu4efNmhf8jNDAwEJ9s+tZbb2HZsmUYPXo0HBwcVJ7Ee+DAAfz8888qt9P+8MMP6N69O3r16gU/Pz/xD3zZk3gPHTok3hL+subMmYP9+/fDw8MDw4cPh5OTE+7du4czZ85g7969uHfvHoDHZ4a2bduG3r17w9/fH6mpqVixYgWcnJwqDGVlevXqhbVr12Lw4MFQKBT49ttvn1mPu7s7AOCzzz7DwIED0aBBAwQEBMDV1RUhISFYuXIlsrKy0LlzZ5w8eRLr1q1Dr1690KVLlxo5HsHBwdi8eTNGjhyJ/fv3o3379igpKcHvv/+OzZs3Iy4uDm3btoWPjw+0tbUREBCA//znP8jNzcWqVatgZmaG27dvV9q/vb099uzZAy8vL/j6+mLfvn3i2I9nef/99zFz5kzs2LED7du3V7mVuEGDBpg7dy6GDBmCzp07IzAwULyN2tbWFuPGjXtm3+7u7ti7d6/4ID87Ozt4eHigZ8+eWL9+PZRKJZycnJCYmIi9e/eKt+CXmThxIn744Qe8/fbbGDt2rHgbdZMmTXDv3j3xDI9CocDy5csRHByMNm3aYODAgTA1NUVaWhp27dqF9u3b4+uvv8Yff/yBbt26oX///nBycoKWlha2b9+OjIyMCh/oR8TbqKleefI26meprduobWxsyrVPSkoSBg0aJFhZWQkNGjQQGjZsKHTr1k1Yt26dUFJSotK2oKBAWLRokeDp6SkoFApBS0tLsLCwEHr27ClER0cLjx49qlJ9T+9bRTIyMoTQ0FDB2tpaaNCggWBhYSF069ZNWLlypdimtLRUmD17tmBjYyPI5XLBzc1N2LlzpxASEqKyr0/eRv2kb775RgAgfPzxx8+tZ9asWcJrr70maGhoqNyGW1xcLMyYMUOws7MTGjRoIFhbWwuTJ08WHj58+Nw+BeF/t1E/T1FRkTB37lyhZcuWglwuFxo2bCi4u7sLM2bMELKzs8V2P//8s+Di4iLo6OgItra2wty5c4U1a9aUuw28ou/DiRMnBENDQ6FTp04V3q5ckTfeeEMAIHzzzTcVLt+0aZPg5uYmyOVywdjYWAgKChL+/vtvlTYV3Ub9+++/C506dRJ0dXUFAOIt1ffv3xeGDBkiNGrUSDAwMBB8fX2F33//XbCxsSl32/XZs2eFjh07CnK5XGjcuLEQEREhLFmyRAAgpKenq7Tdv3+/4OvrKyiVSkFHR0do1qyZ8MEHHwinT58WBEEQ7ty5I4SGhgoODg6Cvr6+oFQqBQ8PD2Hz5s1VOk706pEJQg2dlyYioldeWFgYvv32W+Tm5oqX3IhqA8fAEBHRCykoKFD5fPfuXaxfvx4dOnRgeKFaxzEwRET0Qjw9PeHl5QVHR0dkZGTgu+++Q05OTpXemE70shhgiIjohfTo0QNbt27FypUrIZPJ0KZNG3z33Xfo1KmTukujVwDHwBAREZHkcAwMERERSQ4DDBEREUlOvR0DU1pailu3bsHQ0PC571EhIiKiukEQBDx48ABWVlbQ0Kj8PEu9DTC3bt167vtniIiIqG66ceOGylvjn1ZvA4yhoSGAxwegKo/sri15eUDZu9tu3QL+/5UvapeXlye+VO7WrVviu2ieaqSW4uvqMSMiotqXk5MDa2tr8e94ZeptgHnyPRzqDDBPPstJoag7f4yffMiUQqGoOMCoqfi6esyIiOjf87zhHxzES0RERJLDAENERESSwwBDREREklNvx8AQ0aulpKQExcXF6i6DiJ6jQYMGNfKyTwYYIpI0QRCQnp6OrKwsdZdCRFVkZGQECwuLl3pOGwMMEUlaWXgxMzODnp4eH1xJVIcJgoD8/HxkZmYCACwtLV+4LwYYIpKskpISMbyYmJiouxwiqgJdXV0AQGZmJszMzF74chIH8RKRZJWNedHT01NzJURUHWW/sy8zbo0Bhogkj5eNiKSlJn5nGWCIiIhIchhgiIiISHIYYIiIiEhyGGCIiIhIchhgiIj+ZV5eXhg7dizCwsLQsGFDmJubY9WqVcjLy8OQIUNgaGgIe3t77N69W1znwoUL8PPzg4GBAczNzREcHIw7d+6Iy2NjY9GhQwcYGRnBxMQEPXv2xLVr18Tl169fh0wmw7Zt29ClSxfo6enB1dUViYmJ/+q+E9UUBhgiqj8EAcjLU88kCNUqdd26dWjUqBFOnjyJsWPHYtSoUejXrx/eeustnDlzBj4+PggODkZ+fj6ysrLQtWtXuLm54fTp04iNjUVGRgb69+8v9peXl4fw8HCcPn0aCQkJ0NDQQO/evVFaWqqy3c8++wwff/wxkpOT0bx5cwQGBuLRo0c1cviJ/k0yQajmb51E5OTkQKlUIjs7GwqFQm115OUBBgaPv87NBfT1n93e9pNdtVLH9Tn+T9WVB4P/Lyw3Nxf6FRVW3eJriJo2SxL08OFDpKamws7ODjo6Oqo/PP+2avywenl5oaSkBIcPHwbw+IF8SqUSffr0wffffw/g8ROGLS0tkZiYiL179+Lw4cOIi4sT+/j7779hbW2NlJQUNG/evNw27ty5A1NTU5w/fx6tWrXC9evXYWdnh9WrV2Po0KEAgEuXLqFly5a4fPkyHBwcXvYIEFVZud/dJ1T17zfPwBARqYGLi4v4taamJkxMTODs7CzOMzc3B/D4aaXnzp3D/v37YWBgIE5lgaPsMtGVK1cQGBiIpk2bQqFQwNbWFgCQlpZW6XbLHuNe9lh3IinhqwSIqP7Q03t8JkRd266GBg0aqHyWyWQq88oe9FVaWorc3FwEBARg7ty55fopCyEBAQGwsbHBqlWrYGVlhdLSUrRq1QpFRUWVbvfJbRBJDQMMEdUfMlm9vObYpk0b/Pjjj7C1tYWWVvl/tu/evYuUlBSsWrUKHTt2BAAcOXLk3y6T6F/FS0hERHVcaGgo7t27h8DAQJw6dQrXrl1DXFwchgwZgpKSEjRs2BAmJiZYuXIlrl69in379iE8PFzdZRPVKgYYIqI6zsrKCkePHkVJSQl8fHzg7OyMsLAwGBkZQUNDAxoaGti4cSOSkpLQqlUrjBs3DvPnz1d32US1ipeQiIj+ZQcOHCg37/r16+XmPXmT6Ouvv45t27ZV2qe3tzcuXbpU6fq2trZ4+qZTIyOjcvOIpIJnYIiIiEhyGGCIiIhIchhgiIiISHIYYIiIiEhyGGCIiIhIchhgiIiISHIYYIiIiEhyGGCIiIhIchhgiIiISHIYYIiI6ikvLy+EhYWJn21tbbFo0SK11UNUk/gqASKiV8SpU6egXw/f1k2vJgYYIqJXhKmpqbpLIKoxvIRERPQv8/LywtixYxEWFoaGDRvC3Nwcq1atQl5eHoYMGQJDQ0PY29tj9+7d4joXLlyAn58fDAwMYG5ujuDgYNy5c0dcnpeXh8GDB8PAwACWlpaIjIwst92nLyEtWLAAzs7O0NfXh7W1NUaPHo3c3FxxeVRUFIyMjBAXFwdHR0cYGBige/fuuH37du0cGKJqYIAhonpDEATk5eWpZaruW53XrVuHRo0a4eTJkxg7dixGjRqFfv364a233sKZM2fg4+OD4OBg5OfnIysrC127doWbmxtOnz6N2NhYZGRkoH///mJ/EyZMwMGDB7Fjxw7s2bMHBw4cwJkzZ55Zg4aGBpYsWYKLFy9i3bp12LdvHyZOnKjSJj8/H1999RXWr1+PQ4cOIS0tDR9//HG19pWoNvASEhHVG/n5+TAwMFDLtnNzc6s1vsTV1RVTpkwBAEyePBlz5sxBo0aNMHz4cADA1KlTsXz5cvz222/Yu3cv3NzcMHv2bHH9NWvWwNraGn/88QesrKzw3Xff4YcffkC3bt0APA5IjRs3fmYNTw/w/eKLLzBy5Eh888034vzi4mKsWLECzZo1AwCMGTMGM2fOrPJ+EtUWBhgiIjVwcXERv9bU1ISJiQmcnZ3Feebm5gCAzMxMnDt3Dvv3768wnF27dg0FBQUoKiqCh4eHON/Y2BgtWrR4Zg179+5FREQEfv/9d+Tk5ODRo0d4+PAh8vPzoaenBwDQ09MTwwsAWFpaIjMz88V2mqgGMcAQUb2hp6enMobj3952dTRo0EDls0wmU5knk8kAAKWlpcjNzUVAQADmzp1brh9LS0tcvXq12vVev34dPXv2xKhRo/Dll1/C2NgYR44cwdChQ1FUVCTuT0V1VvdyGVFtqNYYmOXLl8PFxQUKhQIKhQKenp4qg8wePnyI0NBQmJiYwMDAAH379kVGRoZKH2lpafD394eenh7MzMwwYcIEPHr0SKXNgQMH0KZNG8jlctjb2yMqKurF95CIXhkymQz6+vpqmcoCR21o06YNLl68CFtbW9jb26tM+vr6aNasGRo0aIATJ06I69y/fx9//PFHpX0mJSWhtLQUkZGRaNeuHZo3b45bt27V2j4Q1bRqBZjGjRtjzpw5SEpKwunTp9G1a1e8++67uHjxIgBg3Lhx+OWXX7BlyxYcPHgQt27dQp8+fcT1S0pK4O/vj6KiIhw7dgzr1q1DVFQUpk6dKrZJTU2Fv78/unTpguTkZISFhWHYsGGIi4uroV0mIpKW0NBQ3Lt3D4GBgTh16hSuXbuGuLg4DBkyBCUlJTAwMMDQoUMxYcIE7Nu3DxcuXMAHH3wADY3K/4m3t7dHcXExli5dij///BPr16/HihUr/sW9Ino51QowAQEB6NGjB15//XU0b94cX375JQwMDHD8+HFkZ2fju+++w4IFC9C1a1e4u7tj7dq1OHbsGI4fPw4A2LNnDy5duoQffvgBrVu3hp+fH2bNmoVly5ahqKgIALBixQrY2dkhMjISjo6OGDNmDN577z0sXLiw5veeiEgCrKyscPToUZSUlMDHxwfOzs4ICwuDkZGRGFLmz5+Pjh07IiAgAN7e3ujQoQPc3d0r7dPV1RULFizA3Llz0apVK0RHRyMiIuLf2iWilyYTXvBiZklJCbZs2YKQkBCcPXsW6enp6NatG+7fvw8jIyOxnY2NDcLCwjBu3DhMnToVP//8M5KTk8XlqampaNq0Kc6cOQM3Nzd06tQJbdq0UXlWwdq1axEWFobs7Owq15eTkwOlUons7GwoFIoX2cUakZcHlI27y80FnneTgu0nu2qljutz/J+qK08cEFjp3RPVLb6GqGmzJEEPHz5Eamoq7OzsoKOjo+5yiKiKnvW7W9W/39UexHv+/Hl4enri4cOHMDAwwPbt2+Hk5ITk5GRoa2urhBfg8Uj69PR0AEB6ero4sv7J5WXLntUmJycHBQUF0NXVrbCuwsJCFBYWip9zcnKqu2tEREQkEdV+kF2LFi2QnJyMEydOYNSoUQgJCcGlS5dqo7ZqiYiIgFKpFCdra2t1l0RERES1pNoBRltbG/b29nB3d0dERARcXV2xePFiWFhYoKioCFlZWSrtMzIyYGFhAQCwsLAod1dS2efntVEoFJWefQEePwgqOztbnG7cuFHdXSMiIiKJeOlXCZSWlqKwsBDu7u5o0KABEhISxGUpKSlIS0uDp6cnAMDT0xPnz59XeQhSfHw8FAoFnJycxDZP9lHWpqyPysjlcvH27rKJiIiI6qdqjYGZPHky/Pz80KRJEzx48AAxMTE4cOAA4uLioFQqMXToUISHh8PY2BgKhQJjx46Fp6cn2rVrBwDw8fGBk5MTgoODMW/ePKSnp2PKlCkIDQ2FXC4HAIwcORJff/01Jk6ciA8//BD79u3D5s2bsWtX7QxuJSIiIumpVoDJzMzE4MGDcfv2bSiVSri4uCAuLg5vv/02AGDhwoXQ0NBA3759UVhYCF9fX5V3amhqamLnzp0YNWoUPD09oa+vj5CQEJX3atjZ2WHXrl0YN24cFi9ejMaNG2P16tXw9fWtoV0mIiIiqatWgPnuu++euVxHRwfLli3DsmXLKm1jY2ODX3/99Zn9eHl54ezZs9UpjYiIiF4hLz0GhoiIiOjfxgBDREREksMAQ0REkvbBBx+gV69ekuv7Rdja2qo8qV7d/agTAwwRkQQUFBRAX18fV69erXD5xYsX0bdvX9ja2kImk1X5j9Nvv/2Gjh07QkdHB9bW1pg3b95z19m+fTvatWsHpVIJQ0NDtGzZEmFhYeLy6dOno3Xr1lXavtQdOHAAMpkMMpkMGhoaUCqVcHNzw8SJE3H79u0a396pU6cwYsSIKrePiooq94T8F+mnLmKAISJSMy8vL0RFRT2zTXx8PGxsbGBvb1/h8vz8fDRt2hRz5swRHwz6PDk5OfDx8YGNjQ2SkpIwf/58TJ8+HStXrqx0nYSEBAwYMAB9+/bFyZMnkZSUhC+//BLFxcVV2mZd9bL1p6Sk4NatWzh16hQmTZqEvXv3olWrVjh//nwNVfiYqakp9PT06kw/6sQAQ0QkATt27MA777xT6fI33ngD8+fPx8CBA8Xnaj1PdHQ0ioqKsGbNGrRs2RIDBw7Ef//7XyxYsKDSdX755Re0b98eEyZMQIsWLdC8eXP06tVLvPs0KioKM2bMwLlz58QzE2XhbMGCBXB2doa+vj6sra0xevRo5Obmin2XnS2Ii4uDo6MjDAwM0L17d5UzGSUlJQgPD4eRkRFMTEwwceJEPP1O4tjYWHTo0EFs07NnT1y7dk1cfv36dchkMmzatAmdO3eGjo4OoqOjq9R3ZczMzGBhYYHmzZtj4MCBOHr0KExNTTFq1CiVdqtXr4ajoyN0dHTg4OCg8qiRt956C5MmTVJp/88//6BBgwY4dOgQgPKXfp51TA8cOIAhQ4YgOztb/F5Mnz69wn7S0tLw7rvvwsDAAAqFAv3791d5Kn7ZWbX169fD1tYWSqUSAwcOxIMHD8Q2W7duhbOzM3R1dWFiYgJvb2/k5eVV6fi9iGq/zJGk6em3XJcWPRS/dvw8Fhra5d/kq1v0EJefaFNQQRug/JuuidRFEID8fPVsW08PkMlqp+/S0lLs3LkTP/30U432m5iYiE6dOkFbW1uc5+vri7lz5+L+/fto2LBhuXUsLCwQExODCxcuoFWrVuWWDxgwABcuXEBsbCz27t0LAFAqlQAADQ0NLFmyBHZ2dvjzzz8xevRoTJw4UeWPeH5+Pr766iusX78eGhoaeP/99/Hxxx8jOjoaABAZGYmoqCisWbMGjo6OiIyMxPbt29G1a1exj7y8PISHh8PFxQW5ubmYOnUqevfujeTkZGho/O//7Z988gkiIyPh5uYGHR2dKvVdVbq6uhg5ciTGjRuHzMxMmJmZITo6GlOnTsXXX38NNzc3nD17FsOHDxefiRYUFIR58+Zhzpw5kP3/D9OmTZtgZWWFjh07VridZx3Tt956C4sWLcLUqVORkpICADAwMCjXR2lpqRheDh48iEePHiE0NBQDBgzAgQMHxHbXrl3DTz/9hJ07d+L+/fvo378/5syZgy+//BK3b99GYGAg5s2bh969e+PBgwc4fPhwlQPgi2CAIaJ6Iz8fqODf539Fbi6gr187fR8/fhwA4OHhUaP9pqenw87OTmWeubm5uKyiADN27FgcPnwYzs7OsLGxQbt27eDj44OgoCDI5XLo6urCwMAAWlpa5S5lPTlOxtbWFl988QVGjhypEmCKi4uxYsUKNGvWDAAwZswYlYedLlq0CJMnT0afPn0AACtWrEBcXJzKdvr27avyec2aNTA1NcWlS5dUQldYWJjYT1X7rg4HBwcAj8/4mJmZYdq0aYiMjBT7t7Ozw6VLl/Dtt98iJCQE/fv3R1hYGI4cOSIGlpiYGAQGBoqB5mnPOqba2tpQKpWQyWTPvKyYkJCA8+fPIzU1VXwR8vfff4+WLVvi1KlTeOONNwA8DjpRUVEwNDQEAAQHByMhIUEMMI8ePUKfPn1gY2MDAHB2dn7hY1cVvIRERPQvmz17NgwMDMTp8OHDGDlypMq8tLQ0sf2OHTvQs2dPaGhoIC0tTaXd7Nmz/9Xa9fX1sWvXLly9ehVTpkyBgYEBxo8fjzfffBP5zzn9tXfvXnTr1g2vvfYaDA0NERwcjLt376qsp6enJ4YXALC0tBTfn5ednY3bt2+rBDktLS20bdtWZTtXrlxBYGAgmjZtCoVCAVtbWwBQOaYAVNarat/VUXb2QSaTIS8vD9euXcPQoUNVvn9ffPGFeHnL1NQUPj4+4tmm1NRUJCYmIigoqNJtVOWYPs/ly5dhbW0thhcAcHJygpGRES5fvizOs7W1FcMLoPq9cXV1Rbdu3eDs7Ix+/fph1apVuH//fpVreBE8A0NE9Yae3uMzIeradlWNHDkS/fv3Fz8HBQWhb9++KmcDrKysxK9//vlnzJkzR5yfnJwsLjM2Nn7hmi0sLFTGOQAQPz9vIHCzZs3QrFkzDBs2DJ999hmaN2+OTZs2YciQIRW2v379Onr27IlRo0bhyy+/hLGxMY4cOYKhQ4eiqKhIHFDaoEEDlfVkMlm1L0MEBATAxsYGq1atgpWVFUpLS9GqVSsUFRWptNOvrVNm/6/sj7+tra04LmXVqlXlzqRpamqKXwcFBeG///0vli5dipiYGDg7O1d6JqOqx7SmVPS9KS0tFfchPj4ex44dw549e7B06VJ89tlnOHHiRLmzfDWFAYaI6g2ZrPYu49QkY2NjleChq6sLMzOzCu8wunLlCv766y/xnXNaWlqV3olUXZ6envjss89QXFws/nGKj49HixYtKrx8VBlbW1vo6emJAza1tbVRUlKi0iYpKQmlpaWIjIwUx6Fs3ry5WvUqlUpYWlrixIkT6NSpEwDg0aNHSEpKQps2bQAAd+/eRUpKClatWiVehjly5EiN9F0dBQUFWLlyJTp16gRTU1MAj8Pnn3/++cwzKu+++y5GjBiB2NhYxMTEYPDgwZW2rcoxreh78TRHR0fcuHEDN27cEM/CXLp0CVlZWXBycqrS/gKPA0379u3Rvn17TJ06FTY2Nti+fTvCw8Or3Ed1MMAQEdVhO3bsgLe393P/N11UVIRLly6JX9+8eRPJyckwMDAQA8/XX3+N7du3IyEhAQAwaNAgzJgxA0OHDsWkSZNw4cIFLF68GAsXLqx0O9OnT0d+fj569OgBGxsbZGVlYcmSJSguLhZDlq2tLVJTU5GcnIzGjRvD0NAQ9vb2KC4uxtKlSxEQEICjR49ixYoV1T4eH330EebMmYPXX38dDg4OWLBgAbKyssTlDRs2hImJCVauXAlLS0ukpaXhk08+qZG+nyUzMxMPHz7EgwcPkJSUhHnz5uHOnTvYtm2b2GbGjBn473//C6VSie7du6OwsBCnT5/G/fv3xT/y+vr66NWrFz7//HNcvnwZgYGBlW6zKse07OxPQkICXF1doaenV+5nydvbG87OzggKCsKiRYvw6NEjjB49Gp07d67yJbQTJ04gISEBPj4+MDMzw4kTJ/DPP//A0dGxSuu/CI6BISKqw553+3SZW7duwc3NDW5ubrh9+za++uoruLm5YdiwYWKbO3fuqNxOrFQqsWfPHqSmpsLd3R3jx4/H1KlTn/mAs86dO+PPP//E4MGD4eDgAD8/P6Snp2PPnj1o0aIFgMeDaLt3744uXbrA1NQUGzZsgKurKxYsWIC5c+eiVatWiI6ORkRERLWPx/jx4xEcHIyQkBB4enrC0NAQvXv3FpdraGhg48aNSEpKQqtWrTBu3DjMnz+/Rvp+lhYtWsDKygru7u6YM2cOvL29ceHCBZUzGMOGDcPq1auxdu1aODs7o3PnzoiKiip3iSUoKAjnzp1Dx44d0aRJk0q3WZVj+tZbb2HkyJEYMGAATE1NK3xQoUwmw44dO9CwYUN06tQJ3t7eaNq0KTZt2lSlfQcAhUKBQ4cOoUePHmjevDmmTJmCyMhI+Pn5VbmP6pIJtXmPkxrl5ORAqVQiOzsbCoVCbXXk5f3vroiq3KXw9O3OtaW06CFuLHwPAGA9bmvlt1H/fxvHcVv/tduoq3vM6NX18OFDpKamws7ODjo6Ff98StmdO3dgaWmJv//+W7w7iKg+eNbvblX/fvMMDBFRHXXv3j0sWLCA4YWoAhwDQ0RURzVv3hzNmzdXdxlEdRLPwBAREZHkMMAQERGR5DDAEJHk1dN7EYjqrZr4nWWAISLJKnv4WnUem05E6lf2O/v0032rg4N4iUiyNDU1YWRkJL6PRU9Pr9KX3hGR+gmCgPz8fGRmZsLIyEjlNQrVxQBDRJJW9s6eshBDRHWfkZHRc9+39TwMMEQkaTKZDJaWljAzM0NxcbG6yyGi52jQoMFLnXkpwwBDRPWCpqZmjfyjSETSwEG8REREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDnVCjARERF44403YGhoCDMzM/Tq1QspKSkqbby8vCCTyVSmkSNHqrRJS0uDv78/9PT0YGZmhgkTJuDRo0cqbQ4cOIA2bdpALpfD3t4eUVFRL7aHREREVO9UK8AcPHgQoaGhOH78OOLj41FcXAwfHx/k5eWptBs+fDhu374tTvPmzROXlZSUwN/fH0VFRTh27BjWrVuHqKgoTJ06VWyTmpoKf39/dOnSBcnJyQgLC8OwYcMQFxf3krtLRERE9YFWdRrHxsaqfI6KioKZmRmSkpLQqVMncb6enh4sLCwq7GPPnj24dOkS9u7dC3Nzc7Ru3RqzZs3CpEmTMH36dGhra2PFihWws7NDZGQkAMDR0RFHjhzBwoUL4evrW919JCIionrmpcbAZGdnAwCMjY1V5kdHR6NRo0Zo1aoVJk+ejPz8fHFZYmIinJ2dYW5uLs7z9fVFTk4OLl68KLbx9vZW6dPX1xeJiYmV1lJYWIicnByViYiIiOqnap2BeVJpaSnCwsLQvn17tGrVSpw/aNAg2NjYwMrKCr/99hsmTZqElJQUbNu2DQCQnp6uEl4AiJ/T09Of2SYnJwcFBQXQ1dUtV09ERARmzJjxortDREREEvLCASY0NBQXLlzAkSNHVOaPGDFC/NrZ2RmWlpbo1q0brl27hmbNmr14pc8xefJkhIeHi59zcnJgbW1da9sjIiIi9XmhS0hjxozBzp07sX//fjRu3PiZbT08PAAAV69eBQBYWFggIyNDpU3Z57JxM5W1USgUFZ59AQC5XA6FQqEyERERUf1UrQAjCALGjBmD7du3Y9++fbCzs3vuOsnJyQAAS0tLAICnpyfOnz+PzMxMsU18fDwUCgWcnJzENgkJCSr9xMfHw9PTszrlEhERUT1VrQATGhqKH374ATExMTA0NER6ejrS09NRUFAAALh27RpmzZqFpKQkXL9+HT///DMGDx6MTp06wcXFBQDg4+MDJycnBAcH49y5c4iLi8OUKVMQGhoKuVwOABg5ciT+/PNPTJw4Eb///ju++eYbbN68GePGjavh3SciIiIpqlaAWb58ObKzs+Hl5QVLS0tx2rRpEwBAW1sbe/fuhY+PDxwcHDB+/Hj07dsXv/zyi9iHpqYmdu7cCU1NTXh6euL999/H4MGDMXPmTLGNnZ0ddu3ahfj4eLi6uiIyMhKrV6/mLdREREQEoJqDeAVBeOZya2trHDx48Ln92NjY4Ndff31mGy8vL5w9e7Y65REREdErgu9CIiIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIsmpVoCJiIjAG2+8AUNDQ5iZmaFXr15ISUlRafPw4UOEhobCxMQEBgYG6Nu3LzIyMlTapKWlwd/fH3p6ejAzM8OECRPw6NEjlTYHDhxAmzZtIJfLYW9vj6ioqBfbQyIiIqp3qhVgDh48iNDQUBw/fhzx8fEoLi6Gj48P8vLyxDbjxo3DL7/8gi1btuDgwYO4desW+vTpIy4vKSmBv78/ioqKcOzYMaxbtw5RUVGYOnWq2CY1NRX+/v7o0qULkpOTERYWhmHDhiEuLq4GdpmIiIikTqs6jWNjY1U+R0VFwczMDElJSejUqROys7Px3XffISYmBl27dgUArF27Fo6Ojjh+/DjatWuHPXv24NKlS9i7dy/Mzc3RunVrzJo1C5MmTcL06dOhra2NFStWwM7ODpGRkQAAR0dHHDlyBAsXLoSvr28N7ToRERFJ1UuNgcnOzgYAGBsbAwCSkpJQXFwMb29vsY2DgwOaNGmCxMREAEBiYiKcnZ1hbm4utvH19UVOTg4uXrwotnmyj7I2ZX1UpLCwEDk5OSoTERER1U8vHGBKS0sRFhaG9u3bo1WrVgCA9PR0aGtrw8jISKWtubk50tPTxTZPhpey5WXLntUmJycHBQUFFdYTEREBpVIpTtbW1i+6a0RERFTHvXCACQ0NxYULF7Bx48aarOeFTZ48GdnZ2eJ048YNdZdEREREtaRaY2DKjBkzBjt37sShQ4fQuHFjcb6FhQWKioqQlZWlchYmIyMDFhYWYpuTJ0+q9Fd2l9KTbZ6+cykjIwMKhQK6uroV1iSXyyGXy19kd4iIiEhiqnUGRhAEjBkzBtu3b8e+fftgZ2enstzd3R0NGjRAQkKCOC8lJQVpaWnw9PQEAHh6euL8+fPIzMwU28THx0OhUMDJyUls82QfZW3K+iAiIqJXW7XOwISGhiImJgY7duyAoaGhOGZFqVRCV1cXSqUSQ4cORXh4OIyNjaFQKDB27Fh4enqiXbt2AAAfHx84OTkhODgY8+bNQ3p6OqZMmYLQ0FDxDMrIkSPx9ddfY+LEifjwww+xb98+bN68Gbt27arh3SciIiIpqtYZmOXLlyM7OxteXl6wtLQUp02bNoltFi5ciJ49e6Jv377o1KkTLCwssG3bNnG5pqYmdu7cCU1NTXh6euL999/H4MGDMXPmTLGNnZ0ddu3ahfj4eLi6uiIyMhKrV6/mLdREREQEoJpnYARBeG4bHR0dLFu2DMuWLau0jY2NDX799ddn9uPl5YWzZ89WpzwiIiJ6RfBdSERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5DDBEREQkOQwwREREJDkMMERERCQ5WuougKTP9pNdNdpfaZEmgO412icREdUvPANDREREksMAQ0RERJLDAENERESSwwBDREREksMAQ0RERJLDAENERESSwwBDREREksMAQ0RERJLDAENERESSwwBDREREksMAQ0RERJJT7QBz6NAhBAQEwMrKCjKZDD/99JPK8g8++AAymUxl6t5d9b029+7dQ1BQEBQKBYyMjDB06FDk5uaqtPntt9/QsWNH6OjowNraGvPmzav+3hEREVG9VO0Ak5eXB1dXVyxbtqzSNt27d8ft27fFacOGDSrLg4KCcPHiRcTHx2Pnzp04dOgQRowYIS7PycmBj48PbGxskJSUhPnz52P69OlYuXJldcslIiKieqjab6P28/ODn5/fM9vI5XJYWFhUuOzy5cuIjY3FqVOn0LZtWwDA0qVL0aNHD3z11VewsrJCdHQ0ioqKsGbNGmhra6Nly5ZITk7GggULVIIOERERvZpqZQzMgQMHYGZmhhYtWmDUqFG4e/euuCwxMRFGRkZieAEAb29vaGho4MSJE2KbTp06QVtbW2zj6+uLlJQU3L9/v8JtFhYWIicnR2UiIiKi+qnGA0z37t3x/fffIyEhAXPnzsXBgwfh5+eHkpISAEB6ejrMzMxU1tHS0oKxsTHS09PFNubm5iptyj6XtXlaREQElEqlOFlbW9f0rhEREVEdUe1LSM8zcOBA8WtnZ2e4uLigWbNmOHDgALp161bTmxNNnjwZ4eHh4uecnByGGCIionqq1m+jbtq0KRo1aoSrV68CACwsLJCZmanS5tGjR7h37544bsbCwgIZGRkqbco+Vza2Ri6XQ6FQqExERERUP9V6gPn7779x9+5dWFpaAgA8PT2RlZWFpKQksc2+fftQWloKDw8Psc2hQ4dQXFwstomPj0eLFi3QsGHD2i6ZiIiI6rhqB5jc3FwkJycjOTkZAJCamork5GSkpaUhNzcXEyZMwPHjx3H9+nUkJCTg3Xffhb29PXx9fQEAjo6O6N69O4YPH46TJ0/i6NGjGDNmDAYOHAgrKysAwKBBg6CtrY2hQ4fi4sWL2LRpExYvXqxyiYiIiIheXdUOMKdPn4abmxvc3NwAAOHh4XBzc8PUqVOhqamJ3377De+88w6aN2+OoUOHwt3dHYcPH4ZcLhf7iI6OhoODA7p164YePXqgQ4cOKs94USqV2LNnD1JTU+Hu7o7x48dj6tSpvIWaiIiIALzAIF4vLy8IglDp8ri4uOf2YWxsjJiYmGe2cXFxweHDh6tbHhEREb0C+C4kIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcLXUXIEW2n+yqctvSIk0A3QEAjp/HQkO7pJaqIiIienXwDAwRERFJDgMMERERSQ4DDBEREUkOAwwRERFJTrUDzKFDhxAQEAArKyvIZDL89NNPKssFQcDUqVNhaWkJXV1deHt748qVKypt7t27h6CgICgUChgZGWHo0KHIzc1VafPbb7+hY8eO0NHRgbW1NebNm1f9vSMiIqJ6qdoBJi8vD66urli2bFmFy+fNm4clS5ZgxYoVOHHiBPT19eHr64uHDx+KbYKCgnDx4kXEx8dj586dOHToEEaMGCEuz8nJgY+PD2xsbJCUlIT58+dj+vTpWLly5QvsIhEREdU31b6N2s/PD35+fhUuEwQBixYtwpQpU/Duu+8CAL7//nuYm5vjp59+wsCBA3H58mXExsbi1KlTaNu2LQBg6dKl6NGjB7766itYWVkhOjoaRUVFWLNmDbS1tdGyZUskJydjwYIFKkGHiIiIXk01OgYmNTUV6enp8Pb2FucplUp4eHggMTERAJCYmAgjIyMxvACAt7c3NDQ0cOLECbFNp06doK2tLbbx9fVFSkoK7t+/X+G2CwsLkZOTozIRERFR/VSjASY9PR0AYG5urjLf3NxcXJaeng4zMzOV5VpaWjA2NlZpU1EfT27jaREREVAqleJkbW398jtEREREdVK9uQtp8uTJyM7OFqcbN26ouyQiIiKqJTUaYCwsLAAAGRkZKvMzMjLEZRYWFsjMzFRZ/ujRI9y7d0+lTUV9PLmNp8nlcigUCpWJiIiI6qcaDTB2dnawsLBAQkKCOC8nJwcnTpyAp6cnAMDT0xNZWVlISkoS2+zbtw+lpaXw8PAQ2xw6dAjFxcVim/j4eLRo0QINGzasyZKJiIhIgqodYHJzc5GcnIzk5GQAjwfuJicnIy0tDTKZDGFhYfjiiy/w888/4/z58xg8eDCsrKzQq1cvAICjoyO6d++O4cOH4+TJkzh69CjGjBmDgQMHwsrKCgAwaNAgaGtrY+jQobh48SI2bdqExYsXIzw8vMZ2nIiIiKSr2rdRnz59Gl26dBE/l4WKkJAQREVFYeLEicjLy8OIESOQlZWFDh06IDY2Fjo6OuI60dHRGDNmDLp16wYNDQ307dsXS5YsEZcrlUrs2bMHoaGhcHd3R6NGjTB16lTeQk1EREQAXiDAeHl5QRCESpfLZDLMnDkTM2fOrLSNsbExYmJinrkdFxcXHD58uLrlERER0Sug3tyFRERERK8OBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwtdRdA9CyOn8dCQ7ukxvu9Pse/xvskIqJ/D8/AEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5DDAEBERkeQwwBAREZHkMMAQERGR5NR4gJk+fTpkMpnK5ODgIC5/+PAhQkNDYWJiAgMDA/Tt2xcZGRkqfaSlpcHf3x96enowMzPDhAkT8OjRo5oulYiIiCRKqzY6bdmyJfbu3fu/jWj9bzPjxo3Drl27sGXLFiiVSowZMwZ9+vTB0aNHAQAlJSXw9/eHhYUFjh07htu3b2Pw4MFo0KABZs+eXRvlEhERkcTUSoDR0tKChYVFufnZ2dn47rvvEBMTg65duwIA1q5dC0dHRxw/fhzt2rXDnj17cOnSJezduxfm5uZo3bo1Zs2ahUmTJmH69OnQ1taujZKJiIhIQmplDMyVK1dgZWWFpk2bIigoCGlpaQCApKQkFBcXw9vbW2zr4OCAJk2aIDExEQCQmJgIZ2dnmJubi218fX2Rk5ODixcvVrrNwsJC5OTkqExERERUP9V4gPHw8EBUVBRiY2OxfPlypKamomPHjnjw4AHS09Ohra0NIyMjlXXMzc2Rnp4OAEhPT1cJL2XLy5ZVJiIiAkqlUpysra1rdseIiIiozqjxS0h+fn7i1y4uLvDw8ICNjQ02b94MXV3dmt6caPLkyQgPDxc/5+TkMMQQERHVU7V+G7WRkRGaN2+Oq1evwsLCAkVFRcjKylJpk5GRIY6ZsbCwKHdXUtnnisbVlJHL5VAoFCoTERER1U+1HmByc3Nx7do1WFpawt3dHQ0aNEBCQoK4PCUlBWlpafD09AQAeHp64vz588jMzBTbxMfHQ6FQwMnJqbbLJSIiIgmo8UtIH3/8MQICAmBjY4Nbt25h2rRp0NTURGBgIJRKJYYOHYrw8HAYGxtDoVBg7Nix8PT0RLt27QAAPj4+cHJyQnBwMObNm4f09HRMmTIFoaGhkMvlNV0uERERSVCNB5i///4bgYGBuHv3LkxNTdGhQwccP34cpqamAICFCxdCQ0MDffv2RWFhIXx9ffHNN9+I62tqamLnzp0YNWoUPD09oa+vj5CQEMycObOmSyUiIiKJqvEAs3Hjxmcu19HRwbJly7Bs2bJK29jY2ODXX3+t6dKIiIionuC7kIiIiEhyGGCIiIhIchhgiIiISHIYYIiIiEhyGGCIiIhIchhgiIiISHIYYIiIiEhyavw5MERSYPvJrlrr+/oc/1rrm4iIHuMZGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwGGCIiIpIcBhgiIiKSHAYYIiIikhwtdRdAVN/YfrKrVvq9Pse/VvolIpIinoEhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJYYAhIiIiyWGAISIiIslhgCEiIiLJ4ZN4iSSitp7wC/Apv0QkPTwDQ0RERJLDAENERESSwwBDREREksMAQ0RERJLDAENERESSwwBDREREksPbqImo1m7R5u3ZRFRbeAaGiIiIJKdOn4FZtmwZ5s+fj/T0dLi6umLp0qV488031V0WEVURH75HRLWlzgaYTZs2ITw8HCtWrICHhwcWLVoEX19fpKSkwMzMTN3lEZGa8bIX0autzl5CWrBgAYYPH44hQ4bAyckJK1asgJ6eHtasWaPu0oiIiEjN6mSAKSoqQlJSEry9vcV5Ghoa8Pb2RmJiohorIyIiorqgTl5CunPnDkpKSmBubq4y39zcHL///nuF6xQWFqKwsFD8nJ2dDQDIycmp8fpKC/Or3rZIA0DO/6+XBwilNV7Piygtevi/rwvzK6yrpOghyo5eSWE+Sv+l2uvqMaNXQ5NxW9RdQp1yYYavukugV0zZ321BEJ7Zrk4GmBcRERGBGTNmlJtvbW2thmoqdvMbdVdQsZvfDK50mbLsi2e0qU119ZgRvSqUi9RdAb2qHjx4AKVSWenyOhlgGjVqBE1NTWRkZKjMz8jIgIWFRYXrTJ48GeHh4eLn0tJS3Lt3DyYmJpDJZOL8nJwcWFtb48aNG1AoFLWzA/UEj1X18HhVD49X9fB4VQ+PV9XVtWMlCAIePHgAKyurZ7arkwFGW1sb7u7uSEhIQK9evQA8DiQJCQkYM2ZMhevI5XLI5XKVeUZGRpVuQ6FQ1IlvlBTwWFUPj1f18HhVD49X9fB4VV1dOlbPOvNSpk4GGAAIDw9HSEgI2rZtizfffBOLFi1CXl4ehgwZou7SiIiISM3qbIAZMGAA/vnnH0ydOhXp6elo3bo1YmNjyw3sJSIioldPnQ0wADBmzJhKLxm9KLlcjmnTppW73ETl8VhVD49X9fB4VQ+PV/XweFWdVI+VTHjefUpEREREdUydfJAdERER0bMwwBAREZHkMMAQERGR5DDAEBERkeS8UgFm2bJlsLW1hY6ODjw8PHDy5El1l1RnHTp0CAEBAbCysoJMJsNPP/2k7pLqrIiICLzxxhswNDSEmZkZevXqhZSUFHWXVWctX74cLi4u4kOzPD09sXv3bnWXJQlz5syBTCZDWFiYukupk6ZPnw6ZTKYyOTg4qLusOu3mzZt4//33YWJiAl1dXTg7O+P06dPqLqtKXpkAs2nTJoSHh2PatGk4c+YMXF1d4evri8zMTHWXVifl5eXB1dUVy5YtU3cpdd7BgwcRGhqK48ePIz4+HsXFxfDx8UFeXp66S6uTGjdujDlz5iApKQmnT59G165d8e677+LixYvqLq1OO3XqFL799lu4uLiou5Q6rWXLlrh9+7Y4HTlyRN0l1Vn3799H+/bt0aBBA+zevRuXLl1CZGQkGjZsqO7SqkZ4Rbz55ptCaGio+LmkpESwsrISIiIi1FiVNAAQtm/fru4yJCMzM1MAIBw8eFDdpUhGw4YNhdWrV6u7jDrrwYMHwuuvvy7Ex8cLnTt3Fj766CN1l1QnTZs2TXB1dVV3GZIxadIkoUOHDuou44W9EmdgioqKkJSUBG9vb3GehoYGvL29kZiYqMbKqD7Kzs4GABgbG6u5krqvpKQEGzduRF5eHjw9PdVdTp0VGhoKf39/lX/DqGJXrlyBlZUVmjZtiqCgIKSlpam7pDrr559/Rtu2bdGvXz+YmZnBzc0Nq1atUndZVfZKBJg7d+6gpKSk3GsIzM3NkZ6erqaqqD4qLS1FWFgY2rdvj1atWqm7nDrr/PnzMDAwgFwux8iRI7F9+3Y4OTmpu6w6aePGjThz5gwiIiLUXUqd5+HhgaioKMTGxmL58uVITU1Fx44d8eDBA3WXVif9+eefWL58OV5//XXExcVh1KhR+O9//4t169apu7QqqdOvEiCSmtDQUFy4cIHX3Z+jRYsWSE5ORnZ2NrZu3YqQkBAcPHiQIeYpN27cwEcffYT4+Hjo6Oiou5w6z8/PT/zaxcUFHh4esLGxwebNmzF06FA1VlY3lZaWom3btpg9ezYAwM3NDRcuXMCKFSsQEhKi5uqe75U4A9OoUSNoamoiIyNDZX5GRgYsLCzUVBXVN2PGjMHOnTuxf/9+NG7cWN3l1Gna2tqwt7eHu7s7IiIi4OrqisWLF6u7rDonKSkJmZmZaNOmDbS0tKClpYWDBw9iyZIl0NLSQklJibpLrNOMjIzQvHlzXL16Vd2l1EmWlpbl/tPg6Ogomctur0SA0dbWhru7OxISEsR5paWlSEhI4HV3emmCIGDMmDHYvn079u3bBzs7O3WXJDmlpaUoLCxUdxl1Trdu3XD+/HkkJyeLU9u2bREUFITk5GRoamqqu8Q6LTc3F9euXYOlpaW6S6mT2rdvX+6RD3/88QdsbGzUVFH1vDKXkMLDwxESEoK2bdvizTffxKJFi5CXl4chQ4aou7Q6KTc3V+V/LampqUhOToaxsTGaNGmixsrqntDQUMTExGDHjh0wNDQUx1UplUro6uqqubq6Z/LkyfDz80OTJk3w4MEDxMTE4MCBA4iLi1N3aXWOoaFhubFU+vr6MDEx4RirCnz88ccICAiAjY0Nbt26hWnTpkFTUxOBgYHqLq1OGjduHN566y3Mnj0b/fv3x8mTJ7Fy5UqsXLlS3aVVjbpvg/o3LV26VGjSpImgra0tvPnmm8Lx48fVXVKdtX//fgFAuSkkJETdpdU5FR0nAMLatWvVXVqd9OGHHwo2NjaCtra2YGpqKnTr1k3Ys2ePusuSDN5GXbkBAwYIlpaWgra2tvDaa68JAwYMEK5evarusuq0X375RWjVqpUgl8sFBwcHYeXKleouqcpkgiAIaspORERERC/klRgDQ0RERPULAwwRERFJDgMMERERSQ4DDBEREUkOAwwRERFJDgMMERERSQ4DDBEREUkOAwwRSd7169chk8mQnJys7lKI6F/CAENEVVJcXIxJkybB2dkZ+vr6sLKywuDBg3Hr1i11l1bOgQMHIJPJkJWVpe5SiKiWMMAQUZXk5+fjzJkz+Pzzz3HmzBls27YNKSkpeOedd9RdGhG9ghhgiAgA4OXlhTFjxmDMmDFQKpVo1KgRPv/8c5S9bUSpVCI+Ph79+/dHixYt0K5dO3z99ddISkpCWloagP9dytm4cSPeeust6OjooFWrVjh48GCl2/3000/h4eFRbr6rqytmzpwJ4PHbqmfOnInGjRtDLpejdevWiI2NrbC/69evo0uXLgCAhg0bQiaT4YMPPgAAxMbGokOHDjAyMoKJiQl69uyJa9euqax/7NgxtG7dGjo6Omjbti1++umncpenLly4AD8/PxgYGMDc3BzBwcG4c+eOuHzr1q1wdnaGrq4uTExM4O3tjby8vOd8B4ioOhhgiEi0bt06aGlp4eTJk1i8eDEWLFiA1atXV9o+OzsbMpkMRkZGKvMnTJiA8ePH4+zZs/D09ERAQADu3r1bYR9BQUE4efKkSpC4ePEifvvtNwwaNAgAsHjxYkRGRuKrr77Cb7/9Bl9fX7zzzju4cuVKuf6sra3x448/AgBSUlJw+/ZtLF68GACQl5eH8PBwnD59GgkJCdDQ0EDv3r1RWloKAMjJyUFAQACcnZ1x5swZzJo1C5MmTVLpPysrC127doWbmxtOnz6N2NhYZGRkoH///gCA27dvIzAwEB9++CEuX76MAwcOoE+fPuBr54hqmHrfJUlEdUXnzp0FR0dHobS0VJw3adIkwdHRscL2BQUFQps2bYRBgwaJ81JTUwUAwpw5c8R5xcXFQuPGjYW5c+dWum1XV1dh5syZ4ufJkycLHh4e4mcrKyvhyy+/VFnnjTfeEEaPHq2y3bNnzwqC8L+3qd+/f/+Z+/zPP/8IAITz588LgiAIy5cvF0xMTISCggKxzapVq1T6njVrluDj46PSz40bNwQAQkpKipCUlCQAEK5fv/7MbRPRy+EZGCIStWvXDjKZTPzs6emJK1euoKSkRKVdcXEx+vfvD0EQsHz58nL9eHp6il9raWmhbdu2uHz5cqXbDQoKQkxMDABAEARs2LABQUFBAB6fFbl16xbat2+vsk779u2f2WdFrly5gsDAQDRt2hQKhQK2trYAIF4CS0lJgYuLC3R0dMR13nzzTZU+zp07h/3798PAwECcHBwcAADXrl2Dq6srunXrBmdnZ/Tr1w+rVq3C/fv3q1UnET0fAwwRVUtZePnrr78QHx8PhULx0n0GBgYiJSUFZ86cwbFjx3Djxg0MGDCgBqpVFRAQgHv37mHVqlU4ceIETpw4AQAoKiqqch+5ubkICAhAcnKyynTlyhV06tQJmpqaiI+Px+7du+Hk5ISlS5eiRYsWSE1NrfH9IXqVMcAQkajsD3qZ48eP4/XXX4empiaA/4WXK1euYO/evTAxMamwn+PHj4tfP3r0CElJSXB0dKx0u40bN0bnzp0RHR2N6OhovP322zAzMwMAKBQKWFlZ4ejRoyrrHD16FE5OThX2p62tDQAqZ47u3r2LlJQUTJkyBd26dYOjo2O5MyMtWrTA+fPnUVhYKM47deqUSps2bdrg4sWLsLW1hb29vcqkr68PAJDJZGjfvj1mzJiBs2fPQltbG9u3b690/4mo+hhgiEiUlpaG8PBwpKSkYMOGDVi6dCk++ugjAI/Dy3vvvYfTp08jOjoaJSUlSE9PR3p6erkzGMuWLcP27dvx+++/IzQ0FPfv38eHH374zG0HBQVh48aN2LJli3j5qMyECRMwd+5cbNq0CSkpKfjkk0+QnJws1vY0GxsbyGQy7Ny5E//88w9yc3PRsGFDmJiYYOXKlbh69Sr27duH8PBwlfUGDRqE0tJSjBgxApcvX0ZcXBy++uorABAvrYWGhuLevXsIDAzEqVOncO3aNcTFxWHIkCEoKSnBiRMnMHv2bJw+fRppaWnYtm0b/vnnn2cGOCJ6AeoehENEdUPnzp2F0aNHCyNHjhQUCoXQsGFD4dNPPxUH9ZYNlK1o2r9/v0qbmJgY4c033xS0tbUFJycnYd++fc/d/v379wW5XC7o6ekJDx48UFlWUlIiTJ8+XXjttdeEBg0aCK6ursLu3bvF5U8P4hUEQZg5c6ZgYWEhyGQyISQkRBAEQYiPjxccHR0FuVwuuLi4CAcOHBAACNu3bxfXO3r0qODi4iJoa2sL7u7uQkxMjABA+P3338U2f/zxh9C7d2/ByMhI0NXVFRwcHISwsDChtLRUuHTpkuDr6yuYmpoKcrlcaN68ubB06dJqfjeI6HlkgsB7+4jo8XNgWrdujUWLFr1wH9evX4ednR3Onj2L1q1b11ht6hQdHY0hQ4YgOzsburq66i6HiP6flroLICKqS77//ns0bdoUr732Gs6dO4dJkyahf//+DC9EdQwDDBHRE9LT0zF16lSkp6fD0tIS/fr1w5dffqnusojoKbyERERERJLDu5CIiIhIchhgiIiISHIYYIiIiEhyGGCIiIhIchhgiIiISHIYYIiIiEhyGGCIiIhIchhgiIiISHIYYIiIiEhy/g+Gcatn4CAfpwAAAABJRU5ErkJggg==",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "nstds_mi = 1.\n",
        "plot_histogram(p2p_mi, mean_mi, median_mi, std_mi, nstds_mi, \"MI ECG Peak-to-Peak Voltages\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ek-6Lc3s-q77",
        "outputId": "e0e6297c-5899-4a6c-88ca-b700741f188b"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Keeping 14340 / 19028 of normal ECGs\n",
            "Keeping 8616 / 10574 of MI ECGs\n",
            "Norm Matrix Shape: (14340, 1000)\n",
            "MI Matrix Shape: (8616, 1000)\n"
          ]
        }
      ],
      "source": [
        "# Drop data outside 1 standard deviation\n",
        "keep_mask_norm = np.abs(p2p_norm - median_norm) <= std_norm\n",
        "keep_mask_mi = np.abs(p2p_mi - median_mi) <= std_mi\n",
        "\n",
        "print(f\"Keeping {np.sum(keep_mask_norm)} / {p2p_norm.size} of normal ECGs\")\n",
        "print(f\"Keeping {np.sum(keep_mask_mi)} / {p2p_mi.size} of MI ECGs\")\n",
        "\n",
        "norm_filtered = norm[keep_mask_norm]\n",
        "mi_filtered = mi[keep_mask_mi]\n",
        "\n",
        "print(f\"Norm Matrix Shape: {norm_filtered.shape}\")\n",
        "print(f\"MI Matrix Shape: {mi_filtered.shape}\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "f1Vi-XjFBKHr",
        "outputId": "7f8338e3-c564-4570-9d94-0d8d066e4425"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "X Shape: (22956, 1, 1000)\n",
            "y Shape: (22956, 1)\n"
          ]
        }
      ],
      "source": [
        "# Combine data into one representation\n",
        "X = np.expand_dims(np.vstack((norm_filtered, mi_filtered)), axis=1)\n",
        "y = np.vstack([\n",
        "      np.zeros(shape=(norm_filtered.shape[0], 1), dtype=int),\n",
        "      np.ones(shape=(mi_filtered.shape[0], 1), dtype=int)\n",
        "    ])\n",
        "\n",
        "print(f\"X Shape: {X.shape}\")\n",
        "print(f\"y Shape: {y.shape}\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "B_NSTQcc86E3"
      },
      "source": [
        "## Split the Dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "Cb08eI4I80Y6"
      },
      "outputs": [],
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "import tensorflow as tf\n",
        "\n",
        "# Split the dataset into training and testing sets\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=42)\n",
        "\n",
        "# Split the training set into train and validation\n",
        "X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.25, random_state=42)\n",
        "\n",
        "# Split the training set further into train and deployment\n",
        "X_train, X_deploy, y_train, y_deploy = train_test_split(X_train, y_train, test_size=0.05, random_state=42)\n",
        "\n",
        "# Convert all the datasets into TensorFlow tensors\n",
        "X_train = tf.convert_to_tensor(X_train)\n",
        "X_val = tf.convert_to_tensor(X_val)\n",
        "X_test = tf.convert_to_tensor(X_test)\n",
        "X_deploy = tf.convert_to_tensor(X_deploy)\n",
        "y_train = tf.convert_to_tensor(y_train)\n",
        "y_val = tf.convert_to_tensor(y_val)\n",
        "y_test = tf.convert_to_tensor(y_test)\n",
        "y_deploy = tf.convert_to_tensor(y_deploy)\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oVSD4w82I7Ob"
      },
      "source": [
        "## Build and Train a Deep Learning Model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5ppasHgVI6Cl",
        "outputId": "38653501-629c-4584-af3d-6a0d3b9ea755"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Model: \"sequential_8\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " conv1d_25 (Conv1D)          (None, 64, 993)           576       \n",
            "                                                                 \n",
            " batch_normalization_9 (Bat  (None, 64, 993)           3972      \n",
            " chNormalization)                                                \n",
            "                                                                 \n",
            " leaky_re_lu_25 (LeakyReLU)  (None, 64, 993)           0         \n",
            "                                                                 \n",
            " max_pooling1d_25 (MaxPooli  (None, 32, 993)           0         \n",
            " ng1D)                                                           \n",
            "                                                                 \n",
            " conv1d_26 (Conv1D)          (None, 32, 988)           6176      \n",
            "                                                                 \n",
            " leaky_re_lu_26 (LeakyReLU)  (None, 32, 988)           0         \n",
            "                                                                 \n",
            " max_pooling1d_26 (MaxPooli  (None, 16, 988)           0         \n",
            " ng1D)                                                           \n",
            "                                                                 \n",
            " conv1d_27 (Conv1D)          (None, 16, 985)           1040      \n",
            "                                                                 \n",
            " leaky_re_lu_27 (LeakyReLU)  (None, 16, 985)           0         \n",
            "                                                                 \n",
            " max_pooling1d_27 (MaxPooli  (None, 8, 985)            0         \n",
            " ng1D)                                                           \n",
            "                                                                 \n",
            " conv1d_28 (Conv1D)          (None, 8, 983)            200       \n",
            "                                                                 \n",
            " leaky_re_lu_28 (LeakyReLU)  (None, 8, 983)            0         \n",
            "                                                                 \n",
            " max_pooling1d_28 (MaxPooli  (None, 4, 983)            0         \n",
            " ng1D)                                                           \n",
            "                                                                 \n",
            " flatten_9 (Flatten)         (None, 3932)              0         \n",
            "                                                                 \n",
            " dense_18 (Dense)            (None, 1000)              3933000   \n",
            "                                                                 \n",
            " dropout_9 (Dropout)         (None, 1000)              0         \n",
            "                                                                 \n",
            " dense_19 (Dense)            (None, 100)               100100    \n",
            "                                                                 \n",
            " dropout_10 (Dropout)        (None, 100)               0         \n",
            "                                                                 \n",
            " dense_20 (Dense)            (None, 1)                 101       \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 4045165 (15.43 MB)\n",
            "Trainable params: 4043179 (15.42 MB)\n",
            "Non-trainable params: 1986 (7.76 KB)\n",
            "_________________________________________________________________\n"
          ]
        }
      ],
      "source": [
        "# Define the model\n",
        "model = tf.keras.Sequential([\n",
        "    tf.keras.layers.Conv1D(filters=64, kernel_size=8, activation=None, data_format=\"channels_first\", input_shape=(1, 1000)),\n",
        "    tf.keras.layers.BatchNormalization(),\n",
        "    tf.keras.layers.LeakyReLU(),\n",
        "    tf.keras.layers.MaxPooling1D(pool_size=2),\n",
        "    tf.keras.layers.Conv1D(filters=32, kernel_size=6, activation=None, data_format=\"channels_first\"),\n",
        "    tf.keras.layers.LeakyReLU(),\n",
        "    tf.keras.layers.MaxPooling1D(pool_size=2),\n",
        "    tf.keras.layers.Conv1D(filters=16, kernel_size=4, activation=None, data_format=\"channels_first\"),\n",
        "    tf.keras.layers.LeakyReLU(),\n",
        "    tf.keras.layers.MaxPooling1D(pool_size=2),\n",
        "    tf.keras.layers.Conv1D(filters=8, kernel_size=3, activation=None, data_format=\"channels_first\"),\n",
        "    tf.keras.layers.LeakyReLU(),\n",
        "    tf.keras.layers.MaxPooling1D(pool_size=2),\n",
        "    tf.keras.layers.Flatten(),\n",
        "    tf.keras.layers.Dense(1000, activation='relu'),\n",
        "    tf.keras.layers.Dropout(0.2),\n",
        "    tf.keras.layers.Dense(100, activation='relu'),\n",
        "    tf.keras.layers.Dropout(0.2),\n",
        "    tf.keras.layers.Dense(1, activation='sigmoid')\n",
        "])\n",
        "\n",
        "# Compile the model\n",
        "model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
        "\n",
        "# Print the model summary\n",
        "model.summary()\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qMm9C4eVNFmy",
        "outputId": "d1b46bb9-fa3c-43ea-80c8-0b275023de4a"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Epoch 1/25\n",
            "3680/3680 [==============================] - 37s 7ms/step - loss: 0.4761 - accuracy: 0.7849 - val_loss: 0.4123 - val_accuracy: 0.8176\n",
            "Epoch 2/25\n",
            "3680/3680 [==============================] - 29s 8ms/step - loss: 0.3410 - accuracy: 0.8559 - val_loss: 0.6270 - val_accuracy: 0.8267\n",
            "Epoch 3/25\n",
            "3680/3680 [==============================] - 30s 8ms/step - loss: 0.1955 - accuracy: 0.9288 - val_loss: 0.4941 - val_accuracy: 0.8902\n",
            "Epoch 4/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0850 - accuracy: 0.9693 - val_loss: 0.4523 - val_accuracy: 0.9049\n",
            "Epoch 5/25\n",
            "3680/3680 [==============================] - 27s 7ms/step - loss: 0.0630 - accuracy: 0.9795 - val_loss: 0.3578 - val_accuracy: 0.9231\n",
            "Epoch 6/25\n",
            "3680/3680 [==============================] - 27s 7ms/step - loss: 0.0526 - accuracy: 0.9841 - val_loss: 0.5364 - val_accuracy: 0.9255\n",
            "Epoch 7/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0485 - accuracy: 0.9857 - val_loss: 0.6081 - val_accuracy: 0.9235\n",
            "Epoch 8/25\n",
            "3680/3680 [==============================] - 26s 7ms/step - loss: 0.0444 - accuracy: 0.9874 - val_loss: 0.5495 - val_accuracy: 0.9166\n",
            "Epoch 9/25\n",
            "3680/3680 [==============================] - 27s 7ms/step - loss: 0.0387 - accuracy: 0.9889 - val_loss: 0.6600 - val_accuracy: 0.9227\n",
            "Epoch 10/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0303 - accuracy: 0.9915 - val_loss: 0.5896 - val_accuracy: 0.9185\n",
            "Epoch 11/25\n",
            "3680/3680 [==============================] - 26s 7ms/step - loss: 0.0458 - accuracy: 0.9880 - val_loss: 0.4264 - val_accuracy: 0.9049\n",
            "Epoch 12/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0415 - accuracy: 0.9899 - val_loss: 0.9698 - val_accuracy: 0.9138\n",
            "Epoch 13/25\n",
            "3680/3680 [==============================] - 27s 7ms/step - loss: 0.0332 - accuracy: 0.9927 - val_loss: 0.6009 - val_accuracy: 0.9282\n",
            "Epoch 14/25\n",
            "3680/3680 [==============================] - 29s 8ms/step - loss: 0.0375 - accuracy: 0.9901 - val_loss: 0.7099 - val_accuracy: 0.9111\n",
            "Epoch 15/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0296 - accuracy: 0.9938 - val_loss: 0.8945 - val_accuracy: 0.9156\n",
            "Epoch 16/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0389 - accuracy: 0.9914 - val_loss: 1.4355 - val_accuracy: 0.9210\n",
            "Epoch 17/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0340 - accuracy: 0.9921 - val_loss: 0.6935 - val_accuracy: 0.9291\n",
            "Epoch 18/25\n",
            "3680/3680 [==============================] - 29s 8ms/step - loss: 0.0276 - accuracy: 0.9936 - val_loss: 0.7200 - val_accuracy: 0.9284\n",
            "Epoch 19/25\n",
            "3680/3680 [==============================] - 27s 7ms/step - loss: 0.0298 - accuracy: 0.9935 - val_loss: 0.5908 - val_accuracy: 0.9164\n",
            "Epoch 20/25\n",
            "3680/3680 [==============================] - 27s 7ms/step - loss: 0.0292 - accuracy: 0.9940 - val_loss: 0.5536 - val_accuracy: 0.9272\n",
            "Epoch 21/25\n",
            "3680/3680 [==============================] - 26s 7ms/step - loss: 0.0390 - accuracy: 0.9918 - val_loss: 0.5348 - val_accuracy: 0.9227\n",
            "Epoch 22/25\n",
            "3680/3680 [==============================] - 28s 8ms/step - loss: 0.0222 - accuracy: 0.9950 - val_loss: 0.9970 - val_accuracy: 0.9311\n",
            "Epoch 23/25\n",
            "3680/3680 [==============================] - 29s 8ms/step - loss: 0.0300 - accuracy: 0.9929 - val_loss: 1.1204 - val_accuracy: 0.9291\n",
            "Epoch 24/25\n",
            "3680/3680 [==============================] - 29s 8ms/step - loss: 0.0348 - accuracy: 0.9928 - val_loss: 1.1594 - val_accuracy: 0.9276\n",
            "Epoch 25/25\n",
            "3680/3680 [==============================] - 27s 7ms/step - loss: 0.0326 - accuracy: 0.9932 - val_loss: 0.9996 - val_accuracy: 0.9286\n"
          ]
        }
      ],
      "source": [
        "history = model.fit(X_train, y_train, batch_size=4, epochs=25, validation_data=(X_val, y_val))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vvHvSY38e1vY",
        "outputId": "5d52d6a4-1660-494f-8214-4f1111eb1c60"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "574/574 [==============================] - 3s 5ms/step - loss: 1.0250 - accuracy: 0.9290\n",
            "Test Accuracy: 92.90\n"
          ]
        }
      ],
      "source": [
        "test_loss, test_accuracy = model.evaluate(X_test, y_test, batch_size=4)\n",
        "print(f\"Test Accuracy: {test_accuracy*100:.2f}\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NGcQQT0olFof"
      },
      "source": [
        "## Visualize the Results"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 27,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 489
        },
        "id": "Zi3hoWcSlJw0",
        "outputId": "a9226265-622b-4f8e-f1b2-fd34ee90d55b"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<matplotlib.legend.Legend at 0x7f4bb5b09f00>"
            ]
          },
          "execution_count": 27,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Plot the accuracy over time\n",
        "plt.plot(history.history[\"accuracy\"], c=\"r\", label=\"Training Accuracy\")\n",
        "plt.plot(history.history[\"val_accuracy\"], c=\"k\", label=\"Validation Accuracy\")\n",
        "plt.title(\"Train and Validation Accuracy vs Epochs\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Accuracy\")\n",
        "plt.grid()\n",
        "plt.legend(loc=\"lower right\")\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jQr2ejlbnbHk"
      },
      "source": [
        "## Save the Model and Deployment Dataset"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 28,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5lL1ohC-n3NE",
        "outputId": "c95d57b3-0c65-4b64-f04b-6d0af90ee81f"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (6.0.1)\n",
            "Requirement already satisfied: h5py in /usr/local/lib/python3.10/dist-packages (3.9.0)\n",
            "Requirement already satisfied: numpy>=1.17.3 in /usr/local/lib/python3.10/dist-packages (from h5py) (1.23.5)\n"
          ]
        }
      ],
      "source": [
        "!pip install pyyaml h5py"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 29,
      "metadata": {
        "id": "GItfEKu-navc"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "\n",
        "# Save the model\n",
        "path_to_save = os.path.join(MOUNT_DIR, \"MyDrive\", \"datasets\", \"model\")\n",
        "model.save(path_to_save)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 31,
      "metadata": {
        "id": "FD34QmUto9Kw"
      },
      "outputs": [],
      "source": [
        "# Save the deployment dataset as numpy arrays\n",
        "path_to_save = os.path.join(MOUNT_DIR, \"MyDrive\", \"datasets\", \"deploy.npz\")\n",
        "np.savez(path_to_save, ecgs=X_deploy.numpy(), labels=y_deploy.numpy())"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}