enron_email_content_forensic_Federated_learning_approach_final.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/nazma98/NLP-based-Email-Content-Digital-Forensic-using-ML-model-and-Explainable-AI/blob/main/enron_email_content_forensic_Federated_learning_approach_final.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5B-TR-7nef3N",
        "outputId": "1c8d99b7-36ca-43ca-a505-c042d1d8d7d0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "# prompt: mount google drive\n",
        "\n",
        "from google.colab import drive\n",
        "drive.mount('/content/drive')\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "dNuGeTHmfhoi"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import torch\n",
        "#import syft as sy\n",
        "from torch import nn, optim\n",
        "from torch.utils.data import DataLoader, TensorDataset, random_split\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.model_selection import train_test_split"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "JdCuoDYw4pBv"
      },
      "outputs": [],
      "source": [
        "from sklearn.metrics import classification_report"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "id": "CUIeKNu-gQuY"
      },
      "outputs": [],
      "source": [
        "# Load and preprocess data\n",
        "df = pd.read_csv('/content/drive/MyDrive/merged_topic_features_labeled.csv')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "m8pnJKyMhW18",
        "outputId": "c6b17710-b965-4437-95a9-f54d9c0473e1"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Unnamed: 0  doc_id  topic 0  topic 1  topic 2  topic 3  topic 4  topic 5  \\\n",
              "0           0       0        0        0        0        0        0        0   \n",
              "1           1       1        0        0        0        2        0        0   \n",
              "2           2       2        0        0        1        0        0        0   \n",
              "3           3       3        2        1        0        2        1        4   \n",
              "4           4       4        1       17        1       40        7        4   \n",
              "\n",
              "   topic 6  topic 7  topic 8  topic 9  topic 10  topic 11  topic 12  topic 13  \\\n",
              "0        0        0        0        0         0         0         0         0   \n",
              "1        0        0        0       22         0         1         1         0   \n",
              "2        1        0        0        0         0         0         0         1   \n",
              "3        3        0        1        3         1         0         0         1   \n",
              "4       16        1        2       32        14       105        21         1   \n",
              "\n",
              "   topic 14 labeled  \n",
              "0         0   False  \n",
              "1         0   False  \n",
              "2         0   False  \n",
              "3         1   False  \n",
              "4         5   False  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-654407f2-a255-419c-a640-6fe6c3e73b13\" 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>Unnamed: 0</th>\n",
              "      <th>doc_id</th>\n",
              "      <th>topic 0</th>\n",
              "      <th>topic 1</th>\n",
              "      <th>topic 2</th>\n",
              "      <th>topic 3</th>\n",
              "      <th>topic 4</th>\n",
              "      <th>topic 5</th>\n",
              "      <th>topic 6</th>\n",
              "      <th>topic 7</th>\n",
              "      <th>topic 8</th>\n",
              "      <th>topic 9</th>\n",
              "      <th>topic 10</th>\n",
              "      <th>topic 11</th>\n",
              "      <th>topic 12</th>\n",
              "      <th>topic 13</th>\n",
              "      <th>topic 14</th>\n",
              "      <th>labeled</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>22</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>3</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>4</td>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>4</td>\n",
              "      <td>1</td>\n",
              "      <td>17</td>\n",
              "      <td>1</td>\n",
              "      <td>40</td>\n",
              "      <td>7</td>\n",
              "      <td>4</td>\n",
              "      <td>16</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>32</td>\n",
              "      <td>14</td>\n",
              "      <td>105</td>\n",
              "      <td>21</td>\n",
              "      <td>1</td>\n",
              "      <td>5</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-654407f2-a255-419c-a640-6fe6c3e73b13')\"\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-654407f2-a255-419c-a640-6fe6c3e73b13 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-654407f2-a255-419c-a640-6fe6c3e73b13');\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-e92e9057-1c7e-4b5c-9c36-07f03e11b9cd\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-e92e9057-1c7e-4b5c-9c36-07f03e11b9cd')\"\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-e92e9057-1c7e-4b5c-9c36-07f03e11b9cd button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df"
            }
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DAo2FDhFhZfJ",
        "outputId": "3765a58e-8a3a-492d-99ba-213bb913a80c"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Unnamed: 0', 'doc_id', 'topic 0', 'topic 1', 'topic 2', 'topic 3',\n",
              "       'topic 4', 'topic 5', 'topic 6', 'topic 7', 'topic 8', 'topic 9',\n",
              "       'topic 10', 'topic 11', 'topic 12', 'topic 13', 'topic 14', 'labeled'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ],
      "source": [
        "df.columns\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "Z8Y2Gpkng-Es"
      },
      "outputs": [],
      "source": [
        "# List of all features\n",
        "features = [\n",
        "    'topic 0', 'topic 1', 'topic 2', 'topic 3',\n",
        "       'topic 4', 'topic 5', 'topic 6', 'topic 7', 'topic 8', 'topic 9',\n",
        "       'topic 10', 'topic 11', 'topic 12', 'topic 13', 'topic 14'\n",
        "]\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ttBWvoWshRfR",
        "outputId": "7c6566d8-15e4-4dd8-8687-5638cb8c1cfe"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Index(['Unnamed: 0', 'doc_id', 'topic 0', 'topic 1', 'topic 2', 'topic 3',\n",
            "       'topic 4', 'topic 5', 'topic 6', 'topic 7', 'topic 8', 'topic 9',\n",
            "       'topic 10', 'topic 11', 'topic 12', 'topic 13', 'topic 14', 'labeled'],\n",
            "      dtype='object')\n"
          ]
        }
      ],
      "source": [
        "print(df.columns)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "id": "EtKy3rxy08KS"
      },
      "outputs": [],
      "source": [
        "df = df.dropna(subset=['labeled'])  # Drop rows with NaN in 'labeled' column"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "id": "YoHkoV-HhDL5"
      },
      "outputs": [],
      "source": [
        "# Ensure 'legitimate' is the target\n",
        "target = 'labeled'\n",
        "\n",
        "# Separate features and target\n",
        "X = df[features]\n",
        "y = df[target]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "id": "hQUssXU90_cw"
      },
      "outputs": [],
      "source": [
        "# Convert the target variable to a numerical type\n",
        "y = y.astype(int)  #'labeled' should be 0 or 1"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zxFHp7bc1mYL",
        "outputId": "a13b8350-be66-47c2-d06f-a54bebc92a75"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0         0\n",
              "1         0\n",
              "2         0\n",
              "3         0\n",
              "4         0\n",
              "         ..\n",
              "515659    0\n",
              "515660    0\n",
              "515661    0\n",
              "515662    0\n",
              "515663    0\n",
              "Name: labeled, Length: 513700, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ],
      "source": [
        "y"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.utils.data import DataLoader, TensorDataset, random_split\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
        "from collections import Counter\n",
        "from imblearn.over_sampling import SMOTE\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "\n",
        "# Define device\n",
        "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
        "\n",
        "scaler = StandardScaler()\n",
        "X_scaled = scaler.fit_transform(X)\n",
        "\n",
        "# Convert to PyTorch tensors\n",
        "X_tensor = torch.tensor(X_scaled, dtype=torch.float32)\n",
        "y_tensor = torch.tensor(y.values, dtype=torch.int64)\n",
        "\n",
        "# Address class imbalance with SMOTE\n",
        "smote = SMOTE()\n",
        "X_resampled, y_resampled = smote.fit_resample(X_tensor.numpy(), y_tensor.numpy())\n",
        "X_tensor_resampled = torch.tensor(X_resampled, dtype=torch.float32)\n",
        "y_tensor_resampled = torch.tensor(y_resampled, dtype=torch.long)\n",
        "\n",
        "# Combine into a TensorDataset\n",
        "dataset = TensorDataset(X_tensor_resampled, y_tensor_resampled)\n",
        "\n",
        "# Split the dataset into train and test\n",
        "train_size = int(0.7 * len(dataset))\n",
        "test_size = len(dataset) - train_size\n",
        "train_dataset, test_dataset = random_split(dataset, [train_size, test_size])\n",
        "\n",
        "# Calculate sizes for 4 clients, ensuring the sum matches train_size\n",
        "client_base_size = train_size // 4\n",
        "remaining = train_size - (client_base_size * 4)\n",
        "client_sizes = [client_base_size] * 4\n",
        "\n",
        "# Distribute the remaining samples to ensure the sum matches train_size\n",
        "for i in range(remaining):\n",
        "    client_sizes[i] += 1\n",
        "\n",
        "# Further split the training data for 4 clients\n",
        "client_datasets = random_split(train_dataset, client_sizes)\n",
        "\n",
        "print([len(client_dataset) for client_dataset in client_datasets])  # Verify the sizes\n",
        "\n",
        "# Check class distribution in the training set\n",
        "train_labels = [int(y.item()) for _, y in train_dataset]\n",
        "class_counts = Counter(train_labels)\n",
        "print(class_counts)\n",
        "\n",
        "# Define a more complex model\n",
        "class MoreComplexNN(nn.Module):\n",
        "    def __init__(self):\n",
        "        super(MoreComplexNN, self).__init__()\n",
        "        self.fc1 = nn.Linear(X_tensor.shape[1], 256)\n",
        "        self.fc2 = nn.Linear(256, 128)\n",
        "        self.fc3 = nn.Linear(128, 2)\n",
        "\n",
        "    def forward(self, x):\n",
        "        x = torch.relu(self.fc1(x))\n",
        "        x = torch.relu(self.fc2(x))\n",
        "        x = self.fc3(x)\n",
        "        return x\n",
        "\n",
        "global_model = MoreComplexNN().to(device)\n",
        "\n",
        "# Calculate class weights\n",
        "class_weights = torch.tensor([1.0, class_counts[0] / class_counts[1]], dtype=torch.float32).to(device)\n",
        "criterion = nn.CrossEntropyLoss(weight=class_weights)\n",
        "optimizer = optim.Adam(global_model.parameters(), lr=0.001)\n",
        "\n",
        "training_accuracies = []\n",
        "\n",
        "\n",
        "# Train your model (simplified training loop)\n",
        "for epoch in range(10):  # Adjust the number of epochs\n",
        "    global_model.train()\n",
        "    correct = 0\n",
        "    total = 0\n",
        "    for data, target in DataLoader(train_dataset, batch_size=32, shuffle=True):\n",
        "        data, target = data.to(device), target.to(device)\n",
        "        optimizer.zero_grad()\n",
        "        output = global_model(data)\n",
        "        loss = criterion(output, target)\n",
        "        loss.backward()\n",
        "        optimizer.step()\n",
        "\n",
        "        _, predicted = torch.max(output.data, 1)\n",
        "        total += target.size(0)\n",
        "        correct += (predicted == target).sum().item()\n",
        "\n",
        "    accuracy = correct / total\n",
        "    training_accuracies.append(accuracy)\n",
        "    print(f'Epoch {epoch+1}, Loss: {loss.item()}, Training Accuracy: {accuracy:.4f}')\n",
        "\n",
        "# Evaluate the global model on the test dataset\n",
        "test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)\n",
        "global_model.eval()\n",
        "correct = 0\n",
        "total = 0\n",
        "all_preds = []\n",
        "all_targets = []\n",
        "with torch.no_grad():\n",
        "    for data, target in test_loader:\n",
        "        data, target = data.to(device), target.to(device)\n",
        "        output = global_model(data)\n",
        "        _, predicted = torch.max(output.data, 1)\n",
        "        total += target.size(0)\n",
        "        correct += (predicted == target).sum().item()\n",
        "        all_preds.extend(predicted.tolist())\n",
        "        all_targets.extend(target.tolist())\n",
        "\n",
        "accuracy = correct / total\n",
        "print(f\"Test Accuracy: {accuracy:.4f}\")\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7jvH8bku3lR3",
        "outputId": "9dffdd5a-66a6-4b70-e0a4-4a378fa4b0db"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[179180, 179180, 179180, 179180]\n",
            "Counter({0: 358481, 1: 358239})\n",
            "Epoch 1, Loss: 0.5314273834228516, Training Accuracy: 0.6684\n",
            "Epoch 2, Loss: 0.37800779938697815, Training Accuracy: 0.7838\n",
            "Epoch 3, Loss: 0.5059495568275452, Training Accuracy: 0.8172\n",
            "Epoch 4, Loss: 0.186772421002388, Training Accuracy: 0.8347\n",
            "Epoch 5, Loss: 0.25173982977867126, Training Accuracy: 0.8465\n",
            "Epoch 6, Loss: 0.5739980340003967, Training Accuracy: 0.8544\n",
            "Epoch 7, Loss: 0.34990018606185913, Training Accuracy: 0.8610\n",
            "Epoch 8, Loss: 0.3557142913341522, Training Accuracy: 0.8668\n",
            "Epoch 9, Loss: 0.36031803488731384, Training Accuracy: 0.8707\n",
            "Epoch 10, Loss: 0.2380792796611786, Training Accuracy: 0.8742\n",
            "Test Accuracy: 0.8769\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Plot the training accuracy\n",
        "plt.plot(range(1, 10 + 1), training_accuracies, marker='o')\n",
        "plt.title('Training Accuracy over Epochs')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Training Accuracy')\n",
        "plt.grid()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "lOfkgxNtBJ2y",
        "outputId": "7079f0ef-5f29-4453-c9a4-50981de83e10"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Create and display confusion matrix\n",
        "conf_matrix = confusion_matrix(all_targets, all_preds)\n",
        "ConfusionMatrixDisplay(conf_matrix).plot()\n",
        "plt.title('Confusion Matrix')\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "Fwb1Mj3Z5sKJ",
        "outputId": "48d2dc9e-c736-4502-ba3e-9063b7f8dc79"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Generate classification report\n",
        "report = classification_report(all_targets, all_preds, target_names=['Class 0', 'Class 1'])\n",
        "print(\"Classification Report:\\n\", report)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_7PaXO5NGId1",
        "outputId": "1b456579-84f4-4e0e-c97b-19b84bf1cbba"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "     Class 0       0.95      0.80      0.87    153462\n",
            "     Class 1       0.82      0.96      0.89    153704\n",
            "\n",
            "    accuracy                           0.88    307166\n",
            "   macro avg       0.89      0.88      0.88    307166\n",
            "weighted avg       0.89      0.88      0.88    307166\n",
            "\n"
          ]
        }
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}