{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "Q0j2VL4Jbx4C"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf\n",
        "import pandas as pd\n",
        "from sklearn.preprocessing import LabelEncoder\n",
        "from sklearn.model_selection import train_test_split\n",
        "import numpy as np\n",
        "from sklearn.metrics import confusion_matrix, classification_report, roc_curve, roc_auc_score\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.metrics import confusion_matrix, classification_report, roc_curve, roc_auc_score, f1_score\n",
        "from sklearn.metrics import confusion_matrix, classification_report, f1_score, roc_curve, roc_auc_score, accuracy_score\n",
        "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
        "import seaborn as sns"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "urpzOOYBcInE",
        "outputId": "56ceede0-7858-44b8-b4e0-f44334d28352"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')\n",
        "data_folder_path = '/content/drive/'\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "QWTpaifOc2zP"
      },
      "outputs": [],
      "source": [
        "#import os\n",
        "#import pandas as pd\n",
        "\n",
        "# Path to the folder containing CSV files\n",
        "#folder_path = '/content/drive/MyDrive/EpilepsyPrediction/Epilepsydataset/data'"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "id": "LNUirkSmc7wg"
      },
      "outputs": [],
      "source": [
        "\n",
        "# List to store individual dataframes\n",
        "#dfs = []\n",
        "\n",
        "# Loop through each file in the folder\n",
        "#for file_name in os.listdir(folder_path):\n",
        " #   if file_name.endswith('.csv'):\n",
        "      # Extract label class from the last word after an underscore in the file name\n",
        "  #      label_class = file_name.split('_')[-1].split('.')[0]\n",
        "\n",
        "        # Read the CSV file into a dataframe\n",
        "   #     file_path = os.path.join(folder_path, file_name)\n",
        "    #    df = pd.read_csv(file_path)\n",
        "\n",
        "        # Add a new column for label class\n",
        "     #   df['label_class'] = label_class\n",
        "\n",
        "        # Append the dataframe to the list\n",
        "      #  dfs.append(df)\n",
        "\n",
        "# Concatenate all dataframes into a single dataframe\n",
        "#merged_df = pd.concat(dfs, ignore_index=True)\n",
        "\n",
        "# Save the merged dataframe to a CSV file\n",
        "#output_csv_path = '/content/drive/MyDrive/EpilepsyPrediction/Epilepsydataset/patientdata.csv'\n",
        "#merged_df.to_csv(output_csv_path, index=False)\n",
        "\n",
        "# Display the merged dataframe\n",
        "#print(merged_df)\n",
        "#print(f\"\\nMerged dataframe saved to: {output_csv_path}\")\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "id": "_OSH7Y0reMBn"
      },
      "outputs": [],
      "source": [
        "# Load the dataset\n",
        "data = pd.read_csv(\"/content/drive/MyDrive/dataset/GNN_Dataset/patientdata.csv\")  # Replace with the actual file path"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 273
        },
        "id": "x6L5DgCUed1a",
        "outputId": "5475d672-6845-48cf-d150-993b84e9d4e4"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   # FP1-F7     F7-T7     T7-P7     P7-O1    FP1-F3     F3-C3     C3-P3  \\\n",
              "0  0.000020  0.000016  0.000012  0.000010 -0.000007  0.000032  0.000010   \n",
              "1  0.000022  0.000015  0.000009  0.000012 -0.000006  0.000030  0.000008   \n",
              "2  0.000021  0.000013  0.000009  0.000014 -0.000006  0.000025  0.000012   \n",
              "3  0.000019  0.000013  0.000010  0.000015 -0.000008  0.000023  0.000012   \n",
              "4  0.000019  0.000012  0.000008  0.000017 -0.000009  0.000022  0.000012   \n",
              "\n",
              "      P3-O1    FP2-F4     F4-C4  ...   T8-P8-0     P8-O2     FZ-CZ     CZ-PZ  \\\n",
              "0  0.000024  0.000043  0.000035  ...  0.000021 -0.000037  0.000034  0.000037   \n",
              "1  0.000026  0.000042  0.000032  ...  0.000022 -0.000029  0.000031  0.000038   \n",
              "2  0.000027  0.000040  0.000030  ...  0.000027 -0.000034  0.000029  0.000040   \n",
              "3  0.000030  0.000037  0.000028  ...  0.000033 -0.000042  0.000028  0.000039   \n",
              "4  0.000032  0.000032  0.000024  ...  0.000035 -0.000031  0.000029  0.000037   \n",
              "\n",
              "      P7-T7    T7-FT9  FT9-FT10   FT10-T8   T8-P8-1  label_class  \n",
              "0 -0.000011  0.000008 -0.000014  0.000013  0.000021   noseizures  \n",
              "1 -0.000008  0.000010 -0.000015  0.000012  0.000022   noseizures  \n",
              "2 -0.000009  0.000012 -0.000013  0.000010  0.000027   noseizures  \n",
              "3 -0.000009  0.000009 -0.000012  0.000009  0.000033   noseizures  \n",
              "4 -0.000008  0.000009 -0.000015  0.000006  0.000035   noseizures  \n",
              "\n",
              "[5 rows x 24 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-573f7367-bbd7-4afc-bf4e-e4baf0c472ca\" 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># FP1-F7</th>\n",
              "      <th>F7-T7</th>\n",
              "      <th>T7-P7</th>\n",
              "      <th>P7-O1</th>\n",
              "      <th>FP1-F3</th>\n",
              "      <th>F3-C3</th>\n",
              "      <th>C3-P3</th>\n",
              "      <th>P3-O1</th>\n",
              "      <th>FP2-F4</th>\n",
              "      <th>F4-C4</th>\n",
              "      <th>...</th>\n",
              "      <th>T8-P8-0</th>\n",
              "      <th>P8-O2</th>\n",
              "      <th>FZ-CZ</th>\n",
              "      <th>CZ-PZ</th>\n",
              "      <th>P7-T7</th>\n",
              "      <th>T7-FT9</th>\n",
              "      <th>FT9-FT10</th>\n",
              "      <th>FT10-T8</th>\n",
              "      <th>T8-P8-1</th>\n",
              "      <th>label_class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.000020</td>\n",
              "      <td>0.000016</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>0.000010</td>\n",
              "      <td>-0.000007</td>\n",
              "      <td>0.000032</td>\n",
              "      <td>0.000010</td>\n",
              "      <td>0.000024</td>\n",
              "      <td>0.000043</td>\n",
              "      <td>0.000035</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000021</td>\n",
              "      <td>-0.000037</td>\n",
              "      <td>0.000034</td>\n",
              "      <td>0.000037</td>\n",
              "      <td>-0.000011</td>\n",
              "      <td>0.000008</td>\n",
              "      <td>-0.000014</td>\n",
              "      <td>0.000013</td>\n",
              "      <td>0.000021</td>\n",
              "      <td>noseizures</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.000022</td>\n",
              "      <td>0.000015</td>\n",
              "      <td>0.000009</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>-0.000006</td>\n",
              "      <td>0.000030</td>\n",
              "      <td>0.000008</td>\n",
              "      <td>0.000026</td>\n",
              "      <td>0.000042</td>\n",
              "      <td>0.000032</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000022</td>\n",
              "      <td>-0.000029</td>\n",
              "      <td>0.000031</td>\n",
              "      <td>0.000038</td>\n",
              "      <td>-0.000008</td>\n",
              "      <td>0.000010</td>\n",
              "      <td>-0.000015</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>0.000022</td>\n",
              "      <td>noseizures</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.000021</td>\n",
              "      <td>0.000013</td>\n",
              "      <td>0.000009</td>\n",
              "      <td>0.000014</td>\n",
              "      <td>-0.000006</td>\n",
              "      <td>0.000025</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>0.000027</td>\n",
              "      <td>0.000040</td>\n",
              "      <td>0.000030</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000027</td>\n",
              "      <td>-0.000034</td>\n",
              "      <td>0.000029</td>\n",
              "      <td>0.000040</td>\n",
              "      <td>-0.000009</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>-0.000013</td>\n",
              "      <td>0.000010</td>\n",
              "      <td>0.000027</td>\n",
              "      <td>noseizures</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.000019</td>\n",
              "      <td>0.000013</td>\n",
              "      <td>0.000010</td>\n",
              "      <td>0.000015</td>\n",
              "      <td>-0.000008</td>\n",
              "      <td>0.000023</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>0.000030</td>\n",
              "      <td>0.000037</td>\n",
              "      <td>0.000028</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000033</td>\n",
              "      <td>-0.000042</td>\n",
              "      <td>0.000028</td>\n",
              "      <td>0.000039</td>\n",
              "      <td>-0.000009</td>\n",
              "      <td>0.000009</td>\n",
              "      <td>-0.000012</td>\n",
              "      <td>0.000009</td>\n",
              "      <td>0.000033</td>\n",
              "      <td>noseizures</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.000019</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>0.000008</td>\n",
              "      <td>0.000017</td>\n",
              "      <td>-0.000009</td>\n",
              "      <td>0.000022</td>\n",
              "      <td>0.000012</td>\n",
              "      <td>0.000032</td>\n",
              "      <td>0.000032</td>\n",
              "      <td>0.000024</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000035</td>\n",
              "      <td>-0.000031</td>\n",
              "      <td>0.000029</td>\n",
              "      <td>0.000037</td>\n",
              "      <td>-0.000008</td>\n",
              "      <td>0.000009</td>\n",
              "      <td>-0.000015</td>\n",
              "      <td>0.000006</td>\n",
              "      <td>0.000035</td>\n",
              "      <td>noseizures</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 24 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-573f7367-bbd7-4afc-bf4e-e4baf0c472ca')\"\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-573f7367-bbd7-4afc-bf4e-e4baf0c472ca 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-573f7367-bbd7-4afc-bf4e-e4baf0c472ca');\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-fc5ae617-4144-45cc-b5c6-85687cbbdcd8\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-fc5ae617-4144-45cc-b5c6-85687cbbdcd8')\"\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-fc5ae617-4144-45cc-b5c6-85687cbbdcd8 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ],
      "source": [
        "data.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 532
        },
        "id": "yWB7LFF-efG4",
        "outputId": "d9eda794-e81c-4fef-8dd1-b6799a4816b7"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Visualize the label column\n",
        "label_counts = data['label_class'].value_counts()\n",
        "label_counts.plot(kind='bar')\n",
        "plt.xlabel('Labels')\n",
        "plt.ylabel('Counts')\n",
        "plt.title('Label Distribution')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "7fj-JDNUekeP"
      },
      "outputs": [],
      "source": [
        "# Separate features and labels\n",
        "X = data.drop(\"label_class\", axis=1)\n",
        "y = data[\"label_class\"]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "id": "FAJkju9YemPV"
      },
      "outputs": [],
      "source": [
        "# Convert labels to numerical values\n",
        "label_encoder = LabelEncoder()\n",
        "y_encoded = label_encoder.fit_transform(y)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "id": "xgE8jfq9es_w"
      },
      "outputs": [],
      "source": [
        "# Split the dataset into train and test sets\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y_encoded, test_size=0.2, random_state=42)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "id": "ztTI_K_bey8G"
      },
      "outputs": [],
      "source": [
        "# Standardize the feature data\n",
        "scaler = StandardScaler()\n",
        "X_train_scaled = scaler.fit_transform(X_train)\n",
        "X_test_scaled = scaler.transform(X_test)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "id": "gygMp8KYe1q_"
      },
      "outputs": [],
      "source": [
        "# Convert the data to TensorFlow tensors\n",
        "X_train_tensor = tf.constant(X_train_scaled, dtype=tf.float32)\n",
        "y_train_tensor = tf.constant(y_train, dtype=tf.int32)\n",
        "X_test_tensor = tf.constant(X_test_scaled, dtype=tf.float32)\n",
        "y_test_tensor = tf.constant(y_test, dtype=tf.int32)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "metadata": {
        "id": "oAWoftTPe5gg"
      },
      "outputs": [],
      "source": [
        "# Define the GNN model\n",
        "class GNNModel(tf.keras.Model):\n",
        "    def __init__(self, num_classes):\n",
        "        super(GNNModel, self).__init__()\n",
        "        self.dense1 = tf.keras.layers.Dense(16, activation='relu')\n",
        "        self.dense2 = tf.keras.layers.Dense(num_classes, activation='softmax')\n",
        "\n",
        "    def call(self, inputs):\n",
        "        x = self.dense1(inputs)\n",
        "        x = self.dense2(x)\n",
        "        return x"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "id": "903Nmn5Le6ZC"
      },
      "outputs": [],
      "source": [
        "# Create the GNN model\n",
        "num_classes = len(label_encoder.classes_)\n",
        "model = GNNModel(num_classes)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "id": "56J31UCqfBOP"
      },
      "outputs": [],
      "source": [
        "# Define loss function and optimizer\n",
        "loss_object = tf.keras.losses.SparseCategoricalCrossentropy()\n",
        "optimizer = tf.keras.optimizers.Adam()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {
        "id": "h6WnaTXSfCHn"
      },
      "outputs": [],
      "source": [
        "# Training loop\n",
        "epochs = 50\n",
        "batch_size = 32\n",
        "steps_per_epoch = len(X_train_scaled) // batch_size"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "metadata": {
        "id": "JLKcMxyjfIIQ"
      },
      "outputs": [],
      "source": [
        "train_loss_history = []\n",
        "test_loss_history = []\n",
        "train_accuracy_history = []\n",
        "test_accuracy_history = []"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dQj1L6nbfJLj",
        "outputId": "88afcedf-e0b3-4917-9bb9-1b7f8f9566fe"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/50, Train Loss: 0.3023, Train Accuracy: 0.8778, Test Loss: 0.3035, Test Accuracy: 0.8760\n",
            "Epoch 2/50, Train Loss: 0.2910, Train Accuracy: 0.8831, Test Loss: 0.2915, Test Accuracy: 0.8820\n",
            "Epoch 3/50, Train Loss: 0.2851, Train Accuracy: 0.8861, Test Loss: 0.2854, Test Accuracy: 0.8856\n",
            "Epoch 4/50, Train Loss: 0.2803, Train Accuracy: 0.8879, Test Loss: 0.2804, Test Accuracy: 0.8876\n",
            "Epoch 5/50, Train Loss: 0.2769, Train Accuracy: 0.8893, Test Loss: 0.2772, Test Accuracy: 0.8890\n",
            "Epoch 6/50, Train Loss: 0.2746, Train Accuracy: 0.8903, Test Loss: 0.2754, Test Accuracy: 0.8896\n",
            "Epoch 7/50, Train Loss: 0.2729, Train Accuracy: 0.8910, Test Loss: 0.2740, Test Accuracy: 0.8902\n",
            "Epoch 8/50, Train Loss: 0.2717, Train Accuracy: 0.8917, Test Loss: 0.2730, Test Accuracy: 0.8908\n",
            "Epoch 9/50, Train Loss: 0.2707, Train Accuracy: 0.8920, Test Loss: 0.2723, Test Accuracy: 0.8913\n",
            "Epoch 10/50, Train Loss: 0.2701, Train Accuracy: 0.8923, Test Loss: 0.2718, Test Accuracy: 0.8915\n",
            "Epoch 11/50, Train Loss: 0.2695, Train Accuracy: 0.8926, Test Loss: 0.2713, Test Accuracy: 0.8917\n",
            "Epoch 12/50, Train Loss: 0.2690, Train Accuracy: 0.8929, Test Loss: 0.2708, Test Accuracy: 0.8919\n",
            "Epoch 13/50, Train Loss: 0.2683, Train Accuracy: 0.8930, Test Loss: 0.2702, Test Accuracy: 0.8919\n",
            "Epoch 14/50, Train Loss: 0.2679, Train Accuracy: 0.8931, Test Loss: 0.2700, Test Accuracy: 0.8923\n",
            "Epoch 15/50, Train Loss: 0.2674, Train Accuracy: 0.8932, Test Loss: 0.2695, Test Accuracy: 0.8920\n",
            "Epoch 16/50, Train Loss: 0.2671, Train Accuracy: 0.8932, Test Loss: 0.2692, Test Accuracy: 0.8923\n",
            "Epoch 17/50, Train Loss: 0.2669, Train Accuracy: 0.8935, Test Loss: 0.2691, Test Accuracy: 0.8925\n",
            "Epoch 18/50, Train Loss: 0.2666, Train Accuracy: 0.8937, Test Loss: 0.2688, Test Accuracy: 0.8926\n",
            "Epoch 19/50, Train Loss: 0.2664, Train Accuracy: 0.8936, Test Loss: 0.2686, Test Accuracy: 0.8928\n",
            "Epoch 20/50, Train Loss: 0.2662, Train Accuracy: 0.8936, Test Loss: 0.2685, Test Accuracy: 0.8929\n",
            "Epoch 21/50, Train Loss: 0.2660, Train Accuracy: 0.8938, Test Loss: 0.2683, Test Accuracy: 0.8930\n",
            "Epoch 22/50, Train Loss: 0.2658, Train Accuracy: 0.8937, Test Loss: 0.2681, Test Accuracy: 0.8931\n",
            "Epoch 23/50, Train Loss: 0.2657, Train Accuracy: 0.8937, Test Loss: 0.2679, Test Accuracy: 0.8932\n",
            "Epoch 24/50, Train Loss: 0.2655, Train Accuracy: 0.8937, Test Loss: 0.2677, Test Accuracy: 0.8930\n",
            "Epoch 25/50, Train Loss: 0.2653, Train Accuracy: 0.8938, Test Loss: 0.2676, Test Accuracy: 0.8933\n",
            "Epoch 26/50, Train Loss: 0.2653, Train Accuracy: 0.8939, Test Loss: 0.2675, Test Accuracy: 0.8934\n",
            "Epoch 27/50, Train Loss: 0.2652, Train Accuracy: 0.8938, Test Loss: 0.2676, Test Accuracy: 0.8932\n",
            "Epoch 28/50, Train Loss: 0.2651, Train Accuracy: 0.8938, Test Loss: 0.2674, Test Accuracy: 0.8932\n",
            "Epoch 29/50, Train Loss: 0.2650, Train Accuracy: 0.8938, Test Loss: 0.2675, Test Accuracy: 0.8929\n",
            "Epoch 30/50, Train Loss: 0.2649, Train Accuracy: 0.8938, Test Loss: 0.2673, Test Accuracy: 0.8930\n",
            "Epoch 31/50, Train Loss: 0.2648, Train Accuracy: 0.8940, Test Loss: 0.2673, Test Accuracy: 0.8927\n",
            "Epoch 32/50, Train Loss: 0.2647, Train Accuracy: 0.8940, Test Loss: 0.2673, Test Accuracy: 0.8926\n",
            "Epoch 33/50, Train Loss: 0.2647, Train Accuracy: 0.8940, Test Loss: 0.2672, Test Accuracy: 0.8931\n",
            "Epoch 34/50, Train Loss: 0.2646, Train Accuracy: 0.8941, Test Loss: 0.2670, Test Accuracy: 0.8929\n",
            "Epoch 35/50, Train Loss: 0.2645, Train Accuracy: 0.8943, Test Loss: 0.2668, Test Accuracy: 0.8928\n",
            "Epoch 36/50, Train Loss: 0.2644, Train Accuracy: 0.8943, Test Loss: 0.2667, Test Accuracy: 0.8929\n",
            "Epoch 37/50, Train Loss: 0.2643, Train Accuracy: 0.8944, Test Loss: 0.2664, Test Accuracy: 0.8928\n",
            "Epoch 38/50, Train Loss: 0.2642, Train Accuracy: 0.8945, Test Loss: 0.2664, Test Accuracy: 0.8929\n",
            "Epoch 39/50, Train Loss: 0.2642, Train Accuracy: 0.8945, Test Loss: 0.2663, Test Accuracy: 0.8927\n",
            "Epoch 40/50, Train Loss: 0.2641, Train Accuracy: 0.8944, Test Loss: 0.2663, Test Accuracy: 0.8930\n",
            "Epoch 41/50, Train Loss: 0.2640, Train Accuracy: 0.8943, Test Loss: 0.2662, Test Accuracy: 0.8929\n",
            "Epoch 42/50, Train Loss: 0.2640, Train Accuracy: 0.8944, Test Loss: 0.2662, Test Accuracy: 0.8930\n",
            "Epoch 43/50, Train Loss: 0.2639, Train Accuracy: 0.8944, Test Loss: 0.2661, Test Accuracy: 0.8930\n",
            "Epoch 44/50, Train Loss: 0.2639, Train Accuracy: 0.8944, Test Loss: 0.2661, Test Accuracy: 0.8931\n",
            "Epoch 45/50, Train Loss: 0.2639, Train Accuracy: 0.8944, Test Loss: 0.2661, Test Accuracy: 0.8930\n",
            "Epoch 46/50, Train Loss: 0.2638, Train Accuracy: 0.8944, Test Loss: 0.2660, Test Accuracy: 0.8932\n",
            "Epoch 47/50, Train Loss: 0.2638, Train Accuracy: 0.8945, Test Loss: 0.2660, Test Accuracy: 0.8931\n",
            "Epoch 48/50, Train Loss: 0.2637, Train Accuracy: 0.8944, Test Loss: 0.2660, Test Accuracy: 0.8930\n",
            "Epoch 49/50, Train Loss: 0.2637, Train Accuracy: 0.8944, Test Loss: 0.2660, Test Accuracy: 0.8931\n",
            "Epoch 50/50, Train Loss: 0.2637, Train Accuracy: 0.8944, Test Loss: 0.2660, Test Accuracy: 0.8931\n"
          ]
        }
      ],
      "source": [
        "for epoch in range(epochs):\n",
        "    for step in range(steps_per_epoch):\n",
        "        start = step * batch_size\n",
        "        end = (step + 1) * batch_size\n",
        "        with tf.GradientTape() as tape:\n",
        "            predictions = model(X_train_tensor[start:end])\n",
        "            loss = loss_object(y_train_tensor[start:end], predictions)\n",
        "\n",
        "        gradients = tape.gradient(loss, model.trainable_variables)\n",
        "        optimizer.apply_gradients(zip(gradients, model.trainable_variables))\n",
        "\n",
        "    train_loss = loss_object(y_train_tensor, model(X_train_tensor))\n",
        "    test_loss = loss_object(y_test_tensor, model(X_test_tensor))\n",
        "    train_loss_history.append(train_loss.numpy())\n",
        "    test_loss_history.append(test_loss.numpy())\n",
        "\n",
        "    y_pred_train = np.argmax(model(X_train_tensor).numpy(), axis=1)\n",
        "    y_pred_test = np.argmax(model(X_test_tensor).numpy(), axis=1)\n",
        "\n",
        "    train_accuracy = accuracy_score(y_train, y_pred_train)\n",
        "    test_accuracy = accuracy_score(y_test, y_pred_test)\n",
        "\n",
        "    train_accuracy_history.append(train_accuracy)\n",
        "    test_accuracy_history.append(test_accuracy)\n",
        "\n",
        "    print(f\"Epoch {epoch + 1}/{epochs}, Train Loss: {train_loss:.4f}, Train Accuracy: {train_accuracy:.4f}, Test Loss: {test_loss:.4f}, Test Accuracy: {test_accuracy:.4f}\")\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "id": "A0AfPi7Snbd2"
      },
      "outputs": [],
      "source": [
        "# Evaluation\n",
        "y_pred_train_prob = model(X_train_tensor).numpy()\n",
        "y_pred_test_prob = model(X_test_tensor).numpy()\n",
        "\n",
        "# Convert probabilities to class indices\n",
        "y_pred_train = np.argmax(y_pred_train_prob, axis=1)\n",
        "y_pred_test = np.argmax(y_pred_test_prob, axis=1)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "id": "eJbmwL9qne2l",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1dd23591-0350-4706-ae36-3e1def967f27"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Train F1 Score: 0.8942021946744341\n",
            "Test F1 Score: 0.8929794741171733\n",
            "Train Accuracy: 0.894367164102256\n",
            "Test Accuracy: 0.893128067826863\n"
          ]
        }
      ],
      "source": [
        "# F1 Score\n",
        "f1_train = f1_score(y_train, y_pred_train, average='weighted')\n",
        "f1_test = f1_score(y_test, y_pred_test, average='weighted')\n",
        "\n",
        "# Accuracy\n",
        "train_accuracy = np.mean(np.equal(y_train, y_pred_train))\n",
        "test_accuracy = np.mean(np.equal(y_test, y_pred_test))\n",
        "\n",
        "# Other metrics\n",
        "print(\"Train F1 Score:\", f1_train)\n",
        "print(\"Test F1 Score:\", f1_test)\n",
        "\n",
        "# Accuracy\n",
        "print(\"Train Accuracy:\", train_accuracy)\n",
        "print(\"Test Accuracy:\", test_accuracy)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 21,
      "metadata": {
        "id": "zUFwxWB1ngFN",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "outputId": "3d618889-02a3-4f6c-ac81-b1c16b68b37b"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Confusion Matrix\n",
        "cm_train = confusion_matrix(y_train, y_pred_train)\n",
        "cm_test = confusion_matrix(y_test, y_pred_test)\n",
        "\n",
        "# Plot Accuracy Curve\n",
        "plt.figure(figsize=(10, 6))\n",
        "plt.plot(range(epochs), train_accuracy_history, label='Train Accuracy')\n",
        "plt.plot(range(epochs), test_accuracy_history, label='Test Accuracy')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.title('Accuracy Curve')\n",
        "plt.legend()\n",
        "plt.show()\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 22,
      "metadata": {
        "id": "2O0B9qJ8nmOP",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "outputId": "f9f1eaad-af24-4dd5-85b9-fdd06056084d"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Loss Curve\n",
        "plt.figure(figsize=(10, 6))\n",
        "plt.plot(train_loss_history, label='Train Loss')\n",
        "plt.plot(test_loss_history, label='Test Loss')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Loss')\n",
        "plt.title('Loss Curve')\n",
        "plt.legend()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "metadata": {
        "id": "JPfuijeznpe1"
      },
      "outputs": [],
      "source": [
        "# Classification Report\n",
        "report_train = classification_report(y_train, y_pred_train, target_names=label_encoder.classes_)\n",
        "report_test = classification_report(y_test, y_pred_test, target_names=label_encoder.classes_)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 24,
      "metadata": {
        "id": "KD6iQPzgnuYG",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ad91ed9f-8bbe-4e03-c26a-0357a9032e35"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Train Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "  noseizures       0.87      0.93      0.90    116674\n",
            "    seizures       0.93      0.86      0.89    116388\n",
            "\n",
            "    accuracy                           0.89    233062\n",
            "   macro avg       0.90      0.89      0.89    233062\n",
            "weighted avg       0.90      0.89      0.89    233062\n",
            "\n"
          ]
        }
      ],
      "source": [
        "# Print Confusion Matrix and Classification Report\n",
        "print(\"Train Classification Report:\")\n",
        "print(report_train)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 25,
      "metadata": {
        "id": "aDLuvqbFnvK3",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "293b8d74-f09f-4d85-a6b7-ecfd596956dd"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "  noseizures       0.86      0.93      0.90     28990\n",
            "    seizures       0.93      0.85      0.89     29276\n",
            "\n",
            "    accuracy                           0.89     58266\n",
            "   macro avg       0.90      0.89      0.89     58266\n",
            "weighted avg       0.90      0.89      0.89     58266\n",
            "\n"
          ]
        }
      ],
      "source": [
        "print(\"Test Classification Report:\")\n",
        "print(report_test)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 26,
      "metadata": {
        "id": "HV-O7OeCnxgD",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "5674366a-a21f-4f0c-a745-99d80c066956"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "ROC AUC Train: 0.9533997340216382\n",
            "ROC AUC Test: 0.9527877131684976\n"
          ]
        }
      ],
      "source": [
        "# ROC Curve\n",
        "# Compute ROC AUC score\n",
        "#roc_auc_train = roc_auc_score(y_train, y_pred_train_prob, multi_class='ovr')\n",
        "#oc_auc_test = roc_auc_score(y_test, y_pred_test_prob, multi_class='ovr')\n",
        "\n",
        "from sklearn.metrics import roc_auc_score\n",
        "import numpy as np\n",
        "\n",
        "# Assuming y_pred_train_prob and y_pred_test_prob are the predicted probabilities for each class\n",
        "# You may need to extract the probabilities for each class depending on your model's output\n",
        "# For example, if y_pred_train_prob is of shape (27443, 2), you may need to use y_pred_train_prob[:, 1] for class 1\n",
        "\n",
        "# Calculate ROC AUC score for each class\n",
        "roc_auc_train = []\n",
        "roc_auc_test = []\n",
        "\n",
        "for i in range(num_classes):  # Replace num_classes with the actual number of classes\n",
        "    roc_auc_train.append(roc_auc_score(y_train == i, y_pred_train_prob[:, i]))\n",
        "    roc_auc_test.append(roc_auc_score(y_test == i, y_pred_test_prob[:, i]))\n",
        "\n",
        "# Print or use roc_auc_train and roc_auc_test as needed\n",
        "print(\"ROC AUC Train:\", np.mean(roc_auc_train))\n",
        "print(\"ROC AUC Test:\", np.mean(roc_auc_test))\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(y_pred_train_prob.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nZyfQdk626rN",
        "outputId": "410099cc-ab75-4703-9fb9-2bc6ffbe22d6"
      },
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(233062, 2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "from sklearn.metrics import roc_curve, auc, roc_auc_score\n",
        "import numpy as np\n",
        "\n",
        "# Assuming y_pred_train_prob and y_pred_test_prob are the predicted probabilities for each class\n",
        "# Extract the probabilities for each class\n",
        "y_pred_train_prob = model(X_train_tensor).numpy()\n",
        "y_pred_test_prob = model(X_test_tensor).numpy()\n",
        "\n",
        "# Convert probabilities to class indices\n",
        "y_pred_train = np.argmax(y_pred_train_prob, axis=1)\n",
        "y_pred_test = np.argmax(y_pred_test_prob, axis=1)\n",
        "\n",
        "# Calculate ROC AUC score for each class\n",
        "roc_auc_train = []\n",
        "roc_auc_test = []\n",
        "\n",
        "for i in range(num_classes):  # Replace num_classes with the actual number of classes\n",
        "    roc_auc_train.append(roc_auc_score(y_train == i, y_pred_train_prob[:, i]))\n",
        "    roc_auc_test.append(roc_auc_score(y_test == i, y_pred_test_prob[:, i]))\n",
        "\n",
        "# Print or use roc_auc_train and roc_auc_test as needed\n",
        "print(\"ROC AUC Train:\", np.mean(roc_auc_train))\n",
        "print(\"ROC AUC Test:\", np.mean(roc_auc_test))\n",
        "\n",
        "# Plot ROC curves\n",
        "plt.figure(figsize=(10, 6))\n",
        "\n",
        "for i in range(num_classes):\n",
        "    fpr_train, tpr_train, _ = roc_curve(y_train == i, y_pred_train_prob[:, i])\n",
        "    roc_auc_train_class = auc(fpr_train, tpr_train)\n",
        "    plt.plot(fpr_train, tpr_train, label=f'Train ROC Curve (Class {i + 1}, AUC = {roc_auc_train_class:.2f})')\n",
        "\n",
        "    fpr_test, tpr_test, _ = roc_curve(y_test == i, y_pred_test_prob[:, i])\n",
        "    roc_auc_test_class = auc(fpr_test, tpr_test)\n",
        "    plt.plot(fpr_test, tpr_test, label=f'Test ROC Curve (Class {i + 1}, AUC = {roc_auc_test_class:.2f})')\n",
        "\n",
        "plt.plot([0, 1], [0, 1], 'k--')\n",
        "plt.xlabel('False Positive Rate')\n",
        "plt.ylabel('True Positive Rate')\n",
        "plt.title('Receiver Operating Characteristic (ROC) Curve for each class')\n",
        "plt.legend()\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 599
        },
        "id": "wY7mD5Tu8A-v",
        "outputId": "b598d735-6ac4-4659-d30f-2bef5250dfef"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "ROC AUC Train: 0.9533997340216382\n",
            "ROC AUC Test: 0.9527877131684976\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 38,
      "metadata": {
        "id": "nF1jzlAsn3aS",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 872
        },
        "outputId": "279e81e5-7eb6-4a85-b770-cc37dc84797f"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1500x1000 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Plot Confusion Matrix Heatmap for Train Set\n",
        "plt.figure(figsize=(15, 10))\n",
        "sns.heatmap(cm_train, annot=True, fmt=\"d\", cmap=\"Blues\", xticklabels=label_encoder.classes_, yticklabels=label_encoder.classes_)\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('True')\n",
        "plt.title('Confusion Matrix (Train Set)')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 39,
      "metadata": {
        "id": "nRr-8Dbin_fp",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 872
        },
        "outputId": "20a682a6-6a38-452d-bc54-eea9db205546"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1500x1000 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Plot Confusion Matrix Heatmap for Test Set\n",
        "plt.figure(figsize=(15, 10))\n",
        "sns.heatmap(cm_test, annot=True, fmt=\"d\", cmap=\"Blues\", xticklabels=label_encoder.classes_, yticklabels=label_encoder.classes_)\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('True')\n",
        "plt.title('Confusion Matrix (Test Set)')\n",
        "plt.show()"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}