{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 578
        },
        "id": "ATYZlK6_JySq",
        "outputId": "e39dcb83-91b0-4d2a-e737-75bf3f6d2d26"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training data shape: (125973, 42)\n",
            "Testing data shape: (22544, 42)\n",
            "\n",
            "Training dataset preview:\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "   duration protocol_type   service flag  src_bytes  dst_bytes  land  \\\n",
              "0         0           tcp  ftp_data   SF        491          0     0   \n",
              "1         0           udp     other   SF        146          0     0   \n",
              "2         0           tcp   private   S0          0          0     0   \n",
              "3         0           tcp      http   SF        232       8153     0   \n",
              "4         0           tcp      http   SF        199        420     0   \n",
              "\n",
              "   wrong_fragment  urgent  hot  ...  dst_host_srv_count  \\\n",
              "0               0       0    0  ...                  25   \n",
              "1               0       0    0  ...                   1   \n",
              "2               0       0    0  ...                  26   \n",
              "3               0       0    0  ...                 255   \n",
              "4               0       0    0  ...                 255   \n",
              "\n",
              "   dst_host_same_srv_rate  dst_host_diff_srv_rate  \\\n",
              "0                    0.17                    0.03   \n",
              "1                    0.00                    0.60   \n",
              "2                    0.10                    0.05   \n",
              "3                    1.00                    0.00   \n",
              "4                    1.00                    0.00   \n",
              "\n",
              "   dst_host_same_src_port_rate  dst_host_srv_diff_host_rate  \\\n",
              "0                         0.17                         0.00   \n",
              "1                         0.88                         0.00   \n",
              "2                         0.00                         0.00   \n",
              "3                         0.03                         0.04   \n",
              "4                         0.00                         0.00   \n",
              "\n",
              "   dst_host_serror_rate  dst_host_srv_serror_rate  dst_host_rerror_rate  \\\n",
              "0                  0.00                      0.00                  0.05   \n",
              "1                  0.00                      0.00                  0.00   \n",
              "2                  1.00                      1.00                  0.00   \n",
              "3                  0.03                      0.01                  0.00   \n",
              "4                  0.00                      0.00                  0.00   \n",
              "\n",
              "   dst_host_srv_rerror_rate   labels  \n",
              "0                      0.00   normal  \n",
              "1                      0.00   normal  \n",
              "2                      0.00  neptune  \n",
              "3                      0.01   normal  \n",
              "4                      0.00   normal  \n",
              "\n",
              "[5 rows x 42 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a82608be-53a8-476d-80e9-c3ebcf41e50c\" 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>duration</th>\n",
              "      <th>protocol_type</th>\n",
              "      <th>service</th>\n",
              "      <th>flag</th>\n",
              "      <th>src_bytes</th>\n",
              "      <th>dst_bytes</th>\n",
              "      <th>land</th>\n",
              "      <th>wrong_fragment</th>\n",
              "      <th>urgent</th>\n",
              "      <th>hot</th>\n",
              "      <th>...</th>\n",
              "      <th>dst_host_srv_count</th>\n",
              "      <th>dst_host_same_srv_rate</th>\n",
              "      <th>dst_host_diff_srv_rate</th>\n",
              "      <th>dst_host_same_src_port_rate</th>\n",
              "      <th>dst_host_srv_diff_host_rate</th>\n",
              "      <th>dst_host_serror_rate</th>\n",
              "      <th>dst_host_srv_serror_rate</th>\n",
              "      <th>dst_host_rerror_rate</th>\n",
              "      <th>dst_host_srv_rerror_rate</th>\n",
              "      <th>labels</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>ftp_data</td>\n",
              "      <td>SF</td>\n",
              "      <td>491</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>25</td>\n",
              "      <td>0.17</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.17</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.00</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "      <td>udp</td>\n",
              "      <td>other</td>\n",
              "      <td>SF</td>\n",
              "      <td>146</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.60</td>\n",
              "      <td>0.88</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>private</td>\n",
              "      <td>S0</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>...</td>\n",
              "      <td>26</td>\n",
              "      <td>0.10</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>1.00</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>neptune</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>http</td>\n",
              "      <td>SF</td>\n",
              "      <td>232</td>\n",
              "      <td>8153</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>255</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>http</td>\n",
              "      <td>SF</td>\n",
              "      <td>199</td>\n",
              "      <td>420</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>255</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 42 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-a82608be-53a8-476d-80e9-c3ebcf41e50c')\"\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-a82608be-53a8-476d-80e9-c3ebcf41e50c 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-a82608be-53a8-476d-80e9-c3ebcf41e50c');\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-bfd326bf-4677-47ba-bfa3-2c1051588cb9\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-bfd326bf-4677-47ba-bfa3-2c1051588cb9')\"\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-bfd326bf-4677-47ba-bfa3-2c1051588cb9 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"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Testing dataset preview:\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "   duration protocol_type   service  flag  src_bytes  dst_bytes  land  \\\n",
              "0         5           tcp      smtp    SF       2429        475     0   \n",
              "1         0           udp  domain_u    SF         45        134     0   \n",
              "2         0           udp  domain_u    SF         45         80     0   \n",
              "3      1979           udp     other    SF        145        105     0   \n",
              "4     14462           tcp     other  RSTR          1          0     0   \n",
              "\n",
              "   wrong_fragment  urgent  hot  ...  dst_host_srv_count  \\\n",
              "0               0       0    0  ...                  57   \n",
              "1               0       0    0  ...                 155   \n",
              "2               0       0    0  ...                 255   \n",
              "3               0       0    0  ...                   2   \n",
              "4               0       0    0  ...                   2   \n",
              "\n",
              "   dst_host_same_srv_rate  dst_host_diff_srv_rate  \\\n",
              "0                    0.11                    0.02   \n",
              "1                    0.80                    0.02   \n",
              "2                    1.00                    0.00   \n",
              "3                    0.01                    0.84   \n",
              "4                    0.01                    0.68   \n",
              "\n",
              "   dst_host_same_src_port_rate  dst_host_srv_diff_host_rate  \\\n",
              "0                         0.01                         0.04   \n",
              "1                         0.01                         0.00   \n",
              "2                         0.01                         0.00   \n",
              "3                         1.00                         0.00   \n",
              "4                         1.00                         0.00   \n",
              "\n",
              "   dst_host_serror_rate  dst_host_srv_serror_rate  dst_host_rerror_rate  \\\n",
              "0                   0.0                       0.0                  0.87   \n",
              "1                   0.0                       0.0                  0.00   \n",
              "2                   0.0                       0.0                  0.00   \n",
              "3                   0.0                       0.0                  0.00   \n",
              "4                   0.0                       0.0                  1.00   \n",
              "\n",
              "   dst_host_srv_rerror_rate     labels  \n",
              "0                       0.0     normal  \n",
              "1                       0.0     normal  \n",
              "2                       0.0     normal  \n",
              "3                       0.0     normal  \n",
              "4                       1.0  portsweep  \n",
              "\n",
              "[5 rows x 42 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-837b66bf-f6b3-472c-b09d-7cbf9336e0e4\" 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>duration</th>\n",
              "      <th>protocol_type</th>\n",
              "      <th>service</th>\n",
              "      <th>flag</th>\n",
              "      <th>src_bytes</th>\n",
              "      <th>dst_bytes</th>\n",
              "      <th>land</th>\n",
              "      <th>wrong_fragment</th>\n",
              "      <th>urgent</th>\n",
              "      <th>hot</th>\n",
              "      <th>...</th>\n",
              "      <th>dst_host_srv_count</th>\n",
              "      <th>dst_host_same_srv_rate</th>\n",
              "      <th>dst_host_diff_srv_rate</th>\n",
              "      <th>dst_host_same_src_port_rate</th>\n",
              "      <th>dst_host_srv_diff_host_rate</th>\n",
              "      <th>dst_host_serror_rate</th>\n",
              "      <th>dst_host_srv_serror_rate</th>\n",
              "      <th>dst_host_rerror_rate</th>\n",
              "      <th>dst_host_srv_rerror_rate</th>\n",
              "      <th>labels</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>5</td>\n",
              "      <td>tcp</td>\n",
              "      <td>smtp</td>\n",
              "      <td>SF</td>\n",
              "      <td>2429</td>\n",
              "      <td>475</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>57</td>\n",
              "      <td>0.11</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.87</td>\n",
              "      <td>0.0</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "      <td>udp</td>\n",
              "      <td>domain_u</td>\n",
              "      <td>SF</td>\n",
              "      <td>45</td>\n",
              "      <td>134</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>155</td>\n",
              "      <td>0.80</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0</td>\n",
              "      <td>udp</td>\n",
              "      <td>domain_u</td>\n",
              "      <td>SF</td>\n",
              "      <td>45</td>\n",
              "      <td>80</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>255</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1979</td>\n",
              "      <td>udp</td>\n",
              "      <td>other</td>\n",
              "      <td>SF</td>\n",
              "      <td>145</td>\n",
              "      <td>105</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>2</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.84</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>normal</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>14462</td>\n",
              "      <td>tcp</td>\n",
              "      <td>other</td>\n",
              "      <td>RSTR</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>...</td>\n",
              "      <td>2</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.68</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.00</td>\n",
              "      <td>1.0</td>\n",
              "      <td>portsweep</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 42 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-837b66bf-f6b3-472c-b09d-7cbf9336e0e4')\"\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-837b66bf-f6b3-472c-b09d-7cbf9336e0e4 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-837b66bf-f6b3-472c-b09d-7cbf9336e0e4');\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-541ca9d6-dc65-4ca9-9cb4-0ce5aa4d2481\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-541ca9d6-dc65-4ca9-9cb4-0ce5aa4d2481')\"\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-541ca9d6-dc65-4ca9-9cb4-0ce5aa4d2481 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"
            }
          },
          "metadata": {}
        }
      ],
      "source": [
        "# SECTION 1. IMPORT LIBRARIES\n",
        "\n",
        "\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import time\n",
        "\n",
        "# ML tools\n",
        "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
        "from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score\n",
        "from sklearn.metrics import (\n",
        "    accuracy_score, precision_score, recall_score, f1_score,\n",
        "    confusion_matrix, classification_report, roc_auc_score, roc_curve, auc\n",
        ")\n",
        "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier\n",
        "from sklearn.preprocessing import label_binarize\n",
        "\n",
        "sns.set(style=\"whitegrid\", palette=\"muted\", font_scale=1.1)\n",
        "\n",
        "\n",
        "# 2. LOAD TRAIN & TEST DATA\n",
        "\n",
        "\n",
        "train_path = \"kdd_train.csv\"\n",
        "test_path = \"kdd_test.csv\"\n",
        "\n",
        "df_train = pd.read_csv(train_path)\n",
        "df_test = pd.read_csv(test_path)\n",
        "\n",
        "print(\"Training data shape:\", df_train.shape)\n",
        "print(\"Testing data shape:\", df_test.shape)\n",
        "\n",
        "print(\"\\nTraining dataset preview:\")\n",
        "display(df_train.head())\n",
        "\n",
        "print(\"\\nTesting dataset preview:\")\n",
        "display(df_test.head())\n",
        "\n",
        "\n",
        "#This section imports all the required Python libraries\n",
        "#for data processing, visualisation, and machine learning.\n",
        "#The two CSV files (kdd_train.csv and kdd_test.csv) are loaded into Pandas DataFrames.\n",
        "#This step ensures the dataset is available in memory and ready for preprocessing and analysis.\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "# SECTION 2. DATA EXPLORATION\n",
        "\n",
        "\n",
        "print(\"BASIC INFO (TRAIN)\")\n",
        "print(df_train.info())\n",
        "\n",
        "print(\"\\nBASIC INFO (TEST)\")\n",
        "print(df_test.info())\n",
        "\n",
        "\n",
        "\n",
        "# Missing Values Check\n",
        "\n",
        "\n",
        "print(\"\\nMISSING VALUES (TRAIN)\")\n",
        "print(df_train.isnull().sum().sum(), \"total missing values\")\n",
        "\n",
        "print(\"\\n MISSING VALUES (TEST) \")\n",
        "print(df_test.isnull().sum().sum(), \"total missing values\")\n",
        "\n",
        "\n",
        "# Class Distribution\n",
        "\n",
        "print(\"\\n CLASS DISTRIBUTION — TRAIN\")\n",
        "train_counts = df_train['labels'].value_counts()\n",
        "print(train_counts)\n",
        "\n",
        "plt.figure(figsize=(10,6))\n",
        "sns.barplot(y=train_counts.index, x=train_counts.values, palette=\"viridis\")\n",
        "plt.title(\"Train Set — Class Distribution\")\n",
        "plt.xlabel(\"Count\")\n",
        "plt.ylabel(\"Attack Type\")\n",
        "plt.show()\n",
        "\n",
        "\n",
        "print(\"\\n CLASS DISTRIBUTION — TEST \")\n",
        "test_counts = df_test['labels'].value_counts()\n",
        "print(test_counts)\n",
        "\n",
        "plt.figure(figsize=(10,6))\n",
        "sns.barplot(y=test_counts.index, x=test_counts.values, palette=\"magma\")\n",
        "plt.title(\"Test Set — Class Distribution\")\n",
        "plt.xlabel(\"Count\")\n",
        "plt.ylabel(\"Attack Type\")\n",
        "plt.show()\n",
        "\n",
        "\n",
        "# Detect categorical columns\n",
        "\n",
        "\n",
        "categorical_cols = ['protocol_type', 'service', 'flag']\n",
        "print(\"\\nCategorical Columns:\", categorical_cols)\n",
        "\n",
        "# Verify columns actually exist\n",
        "for col in categorical_cols:\n",
        "    if col not in df_train.columns:\n",
        "        print(f\" Column missing: {col}\")\n",
        "\n",
        "\n",
        "#This section checks the dataset structure, including the number of rows, columns, data types, and missing values.\n",
        "#It also visualises the class distribution to understand how balanced (or imbalanced) the attack categories are.\n",
        "#These insights help inform preprocessing decisions and model selection.\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "dPNRFGY4F4K-",
        "outputId": "2533dde1-c765-41e3-8f92-f383e800b208"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "BASIC INFO (TRAIN)\n",
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 125973 entries, 0 to 125972\n",
            "Data columns (total 42 columns):\n",
            " #   Column                       Non-Null Count   Dtype  \n",
            "---  ------                       --------------   -----  \n",
            " 0   duration                     125973 non-null  int64  \n",
            " 1   protocol_type                125973 non-null  int64  \n",
            " 2   service                      125973 non-null  int64  \n",
            " 3   flag                         125973 non-null  int64  \n",
            " 4   src_bytes                    125973 non-null  int64  \n",
            " 5   dst_bytes                    125973 non-null  int64  \n",
            " 6   land                         125973 non-null  int64  \n",
            " 7   wrong_fragment               125973 non-null  int64  \n",
            " 8   urgent                       125973 non-null  int64  \n",
            " 9   hot                          125973 non-null  int64  \n",
            " 10  num_failed_logins            125973 non-null  int64  \n",
            " 11  logged_in                    125973 non-null  int64  \n",
            " 12  num_compromised              125973 non-null  int64  \n",
            " 13  root_shell                   125973 non-null  int64  \n",
            " 14  su_attempted                 125973 non-null  int64  \n",
            " 15  num_root                     125973 non-null  int64  \n",
            " 16  num_file_creations           125973 non-null  int64  \n",
            " 17  num_shells                   125973 non-null  int64  \n",
            " 18  num_access_files             125973 non-null  int64  \n",
            " 19  num_outbound_cmds            125973 non-null  int64  \n",
            " 20  is_host_login                125973 non-null  int64  \n",
            " 21  is_guest_login               125973 non-null  int64  \n",
            " 22  count                        125973 non-null  int64  \n",
            " 23  srv_count                    125973 non-null  int64  \n",
            " 24  serror_rate                  125973 non-null  float64\n",
            " 25  srv_serror_rate              125973 non-null  float64\n",
            " 26  rerror_rate                  125973 non-null  float64\n",
            " 27  srv_rerror_rate              125973 non-null  float64\n",
            " 28  same_srv_rate                125973 non-null  float64\n",
            " 29  diff_srv_rate                125973 non-null  float64\n",
            " 30  srv_diff_host_rate           125973 non-null  float64\n",
            " 31  dst_host_count               125973 non-null  int64  \n",
            " 32  dst_host_srv_count           125973 non-null  int64  \n",
            " 33  dst_host_same_srv_rate       125973 non-null  float64\n",
            " 34  dst_host_diff_srv_rate       125973 non-null  float64\n",
            " 35  dst_host_same_src_port_rate  125973 non-null  float64\n",
            " 36  dst_host_srv_diff_host_rate  125973 non-null  float64\n",
            " 37  dst_host_serror_rate         125973 non-null  float64\n",
            " 38  dst_host_srv_serror_rate     125973 non-null  float64\n",
            " 39  dst_host_rerror_rate         125973 non-null  float64\n",
            " 40  dst_host_srv_rerror_rate     125973 non-null  float64\n",
            " 41  labels                       125973 non-null  object \n",
            "dtypes: float64(15), int64(26), object(1)\n",
            "memory usage: 40.4+ MB\n",
            "None\n",
            "\n",
            "BASIC INFO (TEST)\n",
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 22544 entries, 0 to 22543\n",
            "Data columns (total 42 columns):\n",
            " #   Column                       Non-Null Count  Dtype  \n",
            "---  ------                       --------------  -----  \n",
            " 0   duration                     22544 non-null  int64  \n",
            " 1   protocol_type                22544 non-null  int64  \n",
            " 2   service                      22544 non-null  int64  \n",
            " 3   flag                         22544 non-null  int64  \n",
            " 4   src_bytes                    22544 non-null  int64  \n",
            " 5   dst_bytes                    22544 non-null  int64  \n",
            " 6   land                         22544 non-null  int64  \n",
            " 7   wrong_fragment               22544 non-null  int64  \n",
            " 8   urgent                       22544 non-null  int64  \n",
            " 9   hot                          22544 non-null  int64  \n",
            " 10  num_failed_logins            22544 non-null  int64  \n",
            " 11  logged_in                    22544 non-null  int64  \n",
            " 12  num_compromised              22544 non-null  int64  \n",
            " 13  root_shell                   22544 non-null  int64  \n",
            " 14  su_attempted                 22544 non-null  int64  \n",
            " 15  num_root                     22544 non-null  int64  \n",
            " 16  num_file_creations           22544 non-null  int64  \n",
            " 17  num_shells                   22544 non-null  int64  \n",
            " 18  num_access_files             22544 non-null  int64  \n",
            " 19  num_outbound_cmds            22544 non-null  int64  \n",
            " 20  is_host_login                22544 non-null  int64  \n",
            " 21  is_guest_login               22544 non-null  int64  \n",
            " 22  count                        22544 non-null  int64  \n",
            " 23  srv_count                    22544 non-null  int64  \n",
            " 24  serror_rate                  22544 non-null  float64\n",
            " 25  srv_serror_rate              22544 non-null  float64\n",
            " 26  rerror_rate                  22544 non-null  float64\n",
            " 27  srv_rerror_rate              22544 non-null  float64\n",
            " 28  same_srv_rate                22544 non-null  float64\n",
            " 29  diff_srv_rate                22544 non-null  float64\n",
            " 30  srv_diff_host_rate           22544 non-null  float64\n",
            " 31  dst_host_count               22544 non-null  int64  \n",
            " 32  dst_host_srv_count           22544 non-null  int64  \n",
            " 33  dst_host_same_srv_rate       22544 non-null  float64\n",
            " 34  dst_host_diff_srv_rate       22544 non-null  float64\n",
            " 35  dst_host_same_src_port_rate  22544 non-null  float64\n",
            " 36  dst_host_srv_diff_host_rate  22544 non-null  float64\n",
            " 37  dst_host_serror_rate         22544 non-null  float64\n",
            " 38  dst_host_srv_serror_rate     22544 non-null  float64\n",
            " 39  dst_host_rerror_rate         22544 non-null  float64\n",
            " 40  dst_host_srv_rerror_rate     22544 non-null  float64\n",
            " 41  labels                       22544 non-null  object \n",
            "dtypes: float64(15), int64(26), object(1)\n",
            "memory usage: 7.2+ MB\n",
            "None\n",
            "\n",
            "MISSING VALUES (TRAIN)\n",
            "0 total missing values\n",
            "\n",
            " MISSING VALUES (TEST) \n",
            "0 total missing values\n",
            "\n",
            " CLASS DISTRIBUTION — TRAIN\n",
            "labels\n",
            "normal             67343\n",
            "neptune            41214\n",
            "satan               3633\n",
            "ipsweep             3599\n",
            "portsweep           2931\n",
            "smurf               2646\n",
            "nmap                1493\n",
            "back                 956\n",
            "teardrop             892\n",
            "warezclient          890\n",
            "pod                  201\n",
            "guess_passwd          53\n",
            "buffer_overflow       30\n",
            "warezmaster           20\n",
            "land                  18\n",
            "imap                  11\n",
            "rootkit               10\n",
            "loadmodule             9\n",
            "ftp_write              8\n",
            "multihop               7\n",
            "phf                    4\n",
            "perl                   3\n",
            "spy                    2\n",
            "Name: count, dtype: int64\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipython-input-1070582354.py:29: FutureWarning: \n",
            "\n",
            "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n",
            "\n",
            "  sns.barplot(y=train_counts.index, x=train_counts.values, palette=\"viridis\")\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            " CLASS DISTRIBUTION — TEST \n",
            "labels\n",
            "normal             11245\n",
            "neptune             6654\n",
            "satan                698\n",
            "smurf                540\n",
            "ipsweep              479\n",
            "guess_passwd         411\n",
            "portsweep            371\n",
            "mscan                310\n",
            "warezmaster          279\n",
            "apache2              228\n",
            "back                 227\n",
            "processtable         211\n",
            "nmap                 206\n",
            "warezclient          107\n",
            "teardrop             104\n",
            "snmpguess             99\n",
            "mailbomb              94\n",
            "saint                 93\n",
            "snmpgetattack         43\n",
            "httptunnel            41\n",
            "pod                   35\n",
            "buffer_overflow       17\n",
            "multihop               9\n",
            "ps                     9\n",
            "sendmail               8\n",
            "rootkit                4\n",
            "loadmodule             4\n",
            "xlock                  4\n",
            "xterm                  3\n",
            "named                  2\n",
            "imap                   2\n",
            "land                   2\n",
            "ftp_write              2\n",
            "xsnoop                 1\n",
            "phf                    1\n",
            "perl                   1\n",
            "Name: count, dtype: int64\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipython-input-1070582354.py:41: FutureWarning: \n",
            "\n",
            "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n",
            "\n",
            "  sns.barplot(y=test_counts.index, x=test_counts.values, palette=\"magma\")\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Categorical Columns: ['protocol_type', 'service', 'flag']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IpTd2Jb8KT5L",
        "outputId": "63e4afc7-0f43-494a-b350-f88e82caed87"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Categorical columns encoded.\n",
            "\n",
            "Unique classes: ['apache2' 'back' 'buffer_overflow' 'ftp_write' 'guess_passwd'\n",
            " 'httptunnel' 'imap' 'ipsweep' 'land' 'loadmodule' 'mailbomb' 'mscan'\n",
            " 'multihop' 'named' 'neptune' 'nmap' 'normal' 'perl' 'phf' 'pod'\n",
            " 'portsweep' 'processtable' 'ps' 'rootkit' 'saint' 'satan' 'sendmail'\n",
            " 'smurf' 'snmpgetattack' 'snmpguess' 'spy' 'teardrop' 'warezclient'\n",
            " 'warezmaster' 'xlock' 'xsnoop' 'xterm']\n",
            "Number of classes: 37\n",
            "\n",
            "Train feature shape: (125973, 41)\n",
            "Test feature shape: (22544, 41)\n",
            "\n",
            "Scaling complete\n"
          ]
        }
      ],
      "source": [
        "\n",
        "# SECTION 3. PREPROCESSING\n",
        "\n",
        "\n",
        "# Identify categorical and numerical columns\n",
        "categorical_cols = ['protocol_type', 'service', 'flag']\n",
        "target_col = 'labels'\n",
        "\n",
        "\n",
        "# 1. Encode categorical columns\n",
        "\n",
        "\n",
        "from sklearn.preprocessing import LabelEncoder # Ensure LabelEncoder is imported\n",
        "\n",
        "label_encoders = {}  # store encoders for consistency\n",
        "\n",
        "for col in categorical_cols:\n",
        "    le = LabelEncoder()\n",
        "    df_train[col] = le.fit_transform(df_train[col])\n",
        "    df_test[col] = le.transform(df_test[col])  # VERY IMPORTANT\n",
        "    label_encoders[col] = le\n",
        "\n",
        "print(\"Categorical columns encoded.\")\n",
        "\n",
        "\n",
        "\n",
        "# 2. Encode target labels\n",
        "\n",
        "\n",
        "label_encoder_y = LabelEncoder()\n",
        "# Fit on the union of all unique labels from both train and test target columns\n",
        "all_labels = pd.concat([df_train[target_col], df_test[target_col]]).unique()\n",
        "label_encoder_y.fit(all_labels)\n",
        "\n",
        "y_train = label_encoder_y.transform(df_train[target_col])\n",
        "y_test = label_encoder_y.transform(df_test[target_col])\n",
        "\n",
        "print(\"\\nUnique classes:\", label_encoder_y.classes_)\n",
        "print(\"Number of classes:\", len(label_encoder_y.classes_))\n",
        "\n",
        "\n",
        "\n",
        "# 3. Prepare feature sets\n",
        "\n",
        "\n",
        "X_train = df_train.drop(columns=[target_col])\n",
        "X_test = df_test.drop(columns=[target_col])\n",
        "\n",
        "print(\"\\nTrain feature shape:\", X_train.shape)\n",
        "print(\"Test feature shape:\", X_test.shape)\n",
        "\n",
        "\n",
        "\n",
        "# 4. Scale numerical features\n",
        "\n",
        "\n",
        "from sklearn.preprocessing import StandardScaler # Ensure StandardScaler is imported\n",
        "\n",
        "scaler = StandardScaler()\n",
        "X_train = scaler.fit_transform(X_train)\n",
        "X_test = scaler.transform(X_test)\n",
        "\n",
        "print(\"\\nScaling complete\")\n",
        "\n",
        "#Categorical features (protocol_type, service, flag) are label-encoded so machine learning models can process them numerically.\n",
        "#The target column (labels) is also encoded into numeric class values.\n",
        "#Finally, all features are scaled using StandardScaler to improve training stability and model performance."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "zo9lIDlaK4_J"
      },
      "outputs": [],
      "source": [
        "\n",
        "# SECTION 4. HELPER FUNCTIONS\n",
        "\n",
        "\n",
        "def plot_conf_matrix(y_true, y_pred, title=\"Confusion Matrix\"):\n",
        "    \"\"\"Plot a normalized confusion matrix.\"\"\"\n",
        "    cm = confusion_matrix(y_true, y_pred)\n",
        "    cm_norm = cm.astype(float) / cm.sum(axis=1)[:, np.newaxis]\n",
        "\n",
        "    plt.figure(figsize=(10, 8))\n",
        "    sns.heatmap(cm_norm, annot=False, cmap=\"viridis\")\n",
        "    plt.title(title + \" (Normalized)\")\n",
        "    plt.xlabel(\"Predicted\")\n",
        "    plt.ylabel(\"Actual\")\n",
        "    plt.show()\n",
        "\n",
        "\n",
        "def evaluate_model(name, model, X_train, X_test, y_train, y_test):\n",
        "    \"\"\"Train, predict, evaluate and visualize results for a given model.\"\"\"\n",
        "\n",
        "\n",
        "    # Training time\n",
        "\n",
        "    start = time.time()\n",
        "    model.fit(X_train, y_train)\n",
        "    train_time = time.time() - start\n",
        "\n",
        "\n",
        "    # Prediction time\n",
        "\n",
        "    start = time.time()\n",
        "    y_pred = model.predict(X_test)\n",
        "    pred_time = time.time() - start\n",
        "\n",
        "    # Compute metrics\n",
        "\n",
        "    acc = accuracy_score(y_test, y_pred)\n",
        "    prec = precision_score(y_test, y_pred, average='weighted', zero_division=0)\n",
        "    rec = recall_score(y_test, y_pred, average='weighted', zero_division=0)\n",
        "    f1 = f1_score(y_test, y_pred, average='weighted', zero_division=0)\n",
        "\n",
        "\n",
        "    # Print results\n",
        "\n",
        "    print(f\"\\n{name} RESULTS\")\n",
        "    print(f\"Training Time: {train_time:.3f}s\")\n",
        "    print(f\"Prediction Time: {pred_time:.3f}s\")\n",
        "    print(f\"Accuracy: {acc:.4f}\")\n",
        "    print(f\"Precision: {prec:.4f}\")\n",
        "    print(f\"Recall: {rec:.4f}\")\n",
        "    print(f\"F1 Score: {f1:.4f}\")\n",
        "\n",
        "    print(\"\\nClassification Report:\")\n",
        "    print(classification_report(y_test, y_pred, zero_division=0))\n",
        "\n",
        "\n",
        "    # Confusion Matrix\n",
        "\n",
        "    plot_conf_matrix(y_test, y_pred, title=name)\n",
        "\n",
        "    # return dictionary for comparison table later\n",
        "    return {\n",
        "        \"Model\": name,\n",
        "        \"Training Time\": train_time,\n",
        "        \"Prediction Time\": pred_time,\n",
        "        \"Accuracy\": acc,\n",
        "        \"Precision\": prec,\n",
        "        \"Recall\": rec,\n",
        "        \"F1 Score\": f1\n",
        "    }, y_pred\n",
        "\n",
        "\n",
        "#Reusable functions are defined to evaluate any classifier.\n",
        "#They calculate accuracy, precision, recall, F1-score, training time and prediction time.\n",
        "#A normalised confusion matrix is also plotted to visually assess classification performance.\n",
        "#Using functions avoids code repetition and keeps the notebook organised."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "yqsPTxT1LbAP",
        "outputId": "2255e2b3-aa85-45fa-f0dc-51730574fcc2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Random Forest (Baseline) RESULTS\n",
            "Training Time: 9.242s\n",
            "Prediction Time: 0.171s\n",
            "Accuracy: 0.9139\n",
            "Precision: 0.8703\n",
            "Recall: 0.9139\n",
            "F1 Score: 0.8766\n",
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.00      0.00      0.00       228\n",
            "           1       0.97      0.99      0.98       227\n",
            "           2       0.88      0.41      0.56        17\n",
            "           3       1.00      0.50      0.67         2\n",
            "           4       1.00      0.02      0.04       411\n",
            "           5       0.00      0.00      0.00        41\n",
            "           6       1.00      1.00      1.00         2\n",
            "           7       0.93      1.00      0.96       479\n",
            "           8       1.00      0.50      0.67         2\n",
            "           9       1.00      0.75      0.86         4\n",
            "          10       0.00      0.00      0.00        94\n",
            "          11       0.00      0.00      0.00       310\n",
            "          12       1.00      0.11      0.20         9\n",
            "          13       0.00      0.00      0.00         2\n",
            "          14       0.99      1.00      1.00      6654\n",
            "          15       1.00      0.99      1.00       206\n",
            "          16       0.87      0.99      0.93     11245\n",
            "          17       1.00      1.00      1.00         1\n",
            "          18       1.00      1.00      1.00         1\n",
            "          19       0.89      0.94      0.92        35\n",
            "          20       0.96      1.00      0.98       371\n",
            "          21       0.00      0.00      0.00       211\n",
            "          22       0.00      0.00      0.00         9\n",
            "          23       1.00      0.25      0.40         4\n",
            "          24       0.00      0.00      0.00        93\n",
            "          25       0.85      1.00      0.92       698\n",
            "          26       0.00      0.00      0.00         8\n",
            "          27       0.99      1.00      1.00       540\n",
            "          28       0.00      0.00      0.00        43\n",
            "          29       0.00      0.00      0.00        99\n",
            "          31       0.89      1.00      0.94       104\n",
            "          32       1.00      1.00      1.00       107\n",
            "          33       0.75      0.01      0.02       279\n",
            "          34       0.00      0.00      0.00         4\n",
            "          35       0.00      0.00      0.00         1\n",
            "          36       0.00      0.00      0.00         3\n",
            "\n",
            "    accuracy                           0.91     22544\n",
            "   macro avg       0.58      0.46      0.47     22544\n",
            "weighted avg       0.87      0.91      0.88     22544\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAyMAAALJCAYAAACne/yVAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAhZ9JREFUeJzs3XlcVdX+//H3QQVEnAHNeSgcEYcyTa0UBzRNTRyRzKs5pGV+ta6mt+nem7M5ZGrOQ6lpapqKmlaapWXlVJpTpqQCTggqILB/f/Tj3IhBOOdw9gFfz+/jPO6Xtdde+8M52x2f81lrb4thGIYAAAAAwMnczA4AAAAAwP2JZAQAAACAKUhGAAAAAJiCZAQAAACAKUhGAAAAAJiCZAQAAACAKUhGAAAAAJiCZAQAAACAKUhGAAAAAJiCZATIY9avX68aNWrowIEDZoeCDNy9e1fBwcF6/fXXzQ7FLhmdZwcOHFCNGjW0fv16p8Rw8OBB1ahRQz/99FOO980vn4MjjBkzRjVq1EjTNnv2bNWoUUMREREmRSW1atVKYWFh1p+Tk5PVrl07PjPgPkMyAvx/qX9o/fUVGBioTp066b333lN8fLzZIeYJqX/EZvbKC0lURESEZs+erePHj+d43w8//FAXL17UsGHD0rS3atUq3Xvx6KOP6plnntHSpUuVkJDgqPDzjYcffljNmzfXO++8I8MwcrTvvT6HLl26KCUlJd1+77//fp45T/ObAgUK6KWXXtK6det04sQJs8MB4CQFzQ4AcDXt2rVTUFCQJOn69evatm2bZs+erZ9++kmLFi0yObq8o3fv3mrQoEG69urVq5sQTc788ccfeu+991S+fHnVqlUr2/slJiZq/vz5euqpp1SmTJl02318fPTqq69KkgzD0JUrV7R161ZNmDBBBw8e1Hvvveew3yE3PPLIIzpy5IgKFnTefzr+8Y9/6B//+Ie+/PJLtWzZMlv73OtzkKTjx49r06ZN6tKliwOjzTuGDh2qQYMGyd3d3exQ0mjfvr0mT56s999/X7NmzTI7HABOQDIC/E3NmjXVuXNn689hYWHq3r27vv76ax07dkx169Y1Mbq8o0GDBmneR0czDEO3b99WkSJFcu0YObV161Zdu3ZNzzzzTIbbvby80r0nYWFhCgoK0s6dOxUTE6PixYs7I1SbuLm5ycPDw6nHbNq0qcqWLauPPvoo28nIvT4HPz8/SdKMGTPUvn17p/xOcXFx8vb2zvXjZFfBggWdmlRml5ubmzp37qxFixYpMjIy02QSQP7BNC3gHgoUKKBHH31UkvT777+n2bZ161a98MILatmypQICAtS4cWMNGDBABw8eTDdOWFiYWrVqpejoaL3yyit69NFHVa9ePYWGhuro0aPp+t+9e1ezZs1Sq1atFBAQoPbt2+ujjz7KNM7IyEiNGzdOLVq0UN26dfX444/rX//6l6KiotL0++u8/zVr1qhDhw4KCAhQu3bttHHjRutYI0eO1KOPPqr69evrhRdeUHR0dE7funs6c+aMRo4cqccee0x169ZVUFCQJk2apLi4uDT9Uqd+ffPNN5o/f77atWungIAALV682Npn+/bt6tu3rxo2bKh69eqpS5cuWrt2bbpjHjp0SEOGDFHz5s1Vt25dNW/eXGFhYfr8888l/TmX/tlnn5UkjR071jql6q9z2zOzbds2eXt7q1GjRtl+Dzw8PFSiRAlZLBYVKlTI2h4ZGalJkyapa9euaty4serWrat27drp3XffTTdl0DAMrVixQl26dFGjRo3UoEEDtW7dWqNGjUr3+Z8/f15jxoyx/v6PP/643nzzTV27du2esWa0ZuSvbRs3blSnTp0UEBCgFi1aaPr06UpOTk43zpUrV/Tvf/9brVq1Ut26dfXYY49p9OjRGa5fcHNzU4sWLfT111/r5s2b94xRuvfn4OnpqZdeekmXLl3SsmXLsjXmzZs3NWHChDQx/9///Z/OnTuXpl9ERIRq1Kih2bNna/v27QoJCVFgYKCGDh0q6X/rJE6ePKkBAwaoYcOGevTRRzVu3Djdvn1bKSkpWrBggdq0aaO6devqqaee0pdffpkunpxcezLy9zUjqXFn9vr7+f/LL7/opZdeUtOmTa3/dqdOnao7d+6kO9axY8f03HPPqX79+nrkkUf04osvZrlW5YknnlBSUpJ27NiRrd8FQN7mel+LAC7o/PnzkqQSJUqkaV+5cqWKFSumkJAQ+fn56dKlS1q3bp369eunFStWqGHDhmn63759W6GhoapTp45eeuklXb16VUuXLtXzzz+vzz//PM03p6+++qq2bt2qJk2a6LnnntONGzc0e/ZsPfDAA+nii4yMVLdu3XTt2jWFhISoZs2aOnHihNauXau9e/dq3bp18vHxSbPPRx99pGvXrql79+7y9vbWxx9/rH/+858qWLCgpk+frkaNGmnEiBE6e/asPvroI40ZMyZH09Ru376d7g9cd3d36+94/PhxhYaGKjk5WX369FGFChX0448/avHixfr222+1atUqFS5cOM3+kydP1p07d9SlSxeVKlVKZcuWlSTNmjVLc+bM0aOPPqrhw4fLw8NDX3/9tcaPH6/ff/9do0ePliT99ttveu6551SqVCn16dNHfn5+un79un7++Wf99NNPat26tdq0aaOkpCTNmzdPPXv2tP5B+/f37++Sk5N18OBB1atXT25uGX/Pk5KSkuY9uXr1qjZu3KhTp06pW7du8vLysm779ddftX37dgUFBalbt24yDEPfffed5s+fr19++UULFiyw9p03b55mzJihJ554Qt27d1ehQoV08eJF7d27V1FRUdZKwPHjxxUWFiZPT09169ZN5cuX17lz57Rq1Sp9++23WrdunYoWLZrl75mZNWvWKDIyUiEhISpVqpR27typ+fPny9vbW4MGDbL2u3Tpknr16qXbt28rJCREVapUUWRkpFatWqV9+/bpk08+Ubly5dKM3aBBA61du1bff/+9dQplZrLzOUjSM888o2XLlumDDz5Q9+7dVbJkyUz7xsXFqXfv3jp9+rQ6duyohg0b6sKFC/roo4+0d+9erVq1Sg8++GCafXbt2qVly5apV69e6tGjR5o1L5GRkerXr5/atWun1q1b69ChQ1q3bp3i4+NVvHhx/fDDD+rZs6cKFCig5cuXa/jw4dq+fbvKly9vHSOn1557KVWqlCZPnpyu/bvvvkt3/dizZ4+GDRumBx54QH379pWPj49OnDihpUuX6scff9Ty5cutVZeff/5Zffv2lZubm/r27asHHnhAX3/9tZ599lndvn07w1gCAgJUqFAhHThwIFtfAgDI4wwAhmEYxv79+w1/f39j2rRpxtWrV42rV68ap0+fNmbMmGH4+/sbLVu2NBISEtLsc+vWrXTjREVFGY0bNzaef/75NO19+/Y1/P39jXnz5qVp/+yzzwx/f39j9erV1rZvvvnG8Pf3N4YNG2akpKRY28+fP2/Uq1fP8Pf3N/bv329tf+WVVwx/f39j06ZNacbesGGD4e/vb7z22mvpfs9mzZoZN27csLZHR0cbdevWNWrUqGF88MEHacb5z3/+Y/j7+xtnz57N9P1L9cknnxj+/v4Zvl588UVrvz59+hg1atQwDh48mGb/2bNnG/7+/sacOXPSjdm6dWsjLi4uTf+ff/7ZqFGjhvHvf/87XSxvv/22UbNmTeP8+fOGYRjGsmXLDH9/f+PQoUNZ/g6p79Enn3xyz9831YULFwx/f3/j9ddfz3B7y5YtM3xPatasaUydOjXN52wYhnHnzh0jOTk53TjTp083/P39jcOHD1vbunTpYrRv3/6eMXbu3Nlo1aqVcf369TTthw8fNmrVqmXMnj3b2pb6nv/1PMvofcnsfEpOTjbat29vNGvWLM2xXnjhBeORRx6xfiapLly4YNSvX98YM2ZMuri///57w9/f33j//ffv+Ttm53No3bq1YRiG8eWXXxr+/v7Gf/7zH+v2OXPmpPu9U68Bc+fOTTPWgQMHDH9/f6Nfv37pjl+7dm3j119/zfD4/v7+xmeffZamfejQoUaNGjWMzp07p7nO/PLLL9br0l/l5Nrzz3/+0/D390/TNmvWLMPf39+4cOFCunFS/frrr0ajRo2M4OBg6zkTHx9vNGvWzAgJCUl3PQwPDzf8/f2N9evXW9v69Olj1KxZ0zh69Giavv/6178Mf39/o2/fvhkeu3Xr1kabNm0yjQ1A/sE0LeBv5s+fr6ZNm6pp06bq0KGD3n//fTVv3lxLlixJt9jzr99kx8XF6fr16ypQoIACAwN1+PDhdGO7ubnpueeeS9P22GOPSVKa6R6p0xMGDRoki8Viba9YsaI6deqUZv+UlBR9/vnnqlq1arptnTt3VqVKlbRz5850dyPq1q1bmvUJPj4+qlq1qiwWi3WaUqrGjRuni/FeBg0apCVLlqR5pd7Z6Nq1azp48KCaNWuWbirNgAED5OXlleEUjdDQ0HRrRDZv3izDMBQSEqJr166lebVq1UopKSn65ptvJEnFihWTJH3++ecOvztaasXj79Wzv/Lz80vzfkydOlUdO3bUggULNGHChDR9PT09rd/s3717Vzdu3NC1a9fUrFkzSdKRI0esfYsWLarIyEh99913mR775MmTOn78uJ566ilrhSb1VaFCBVWqVElff/21rb9+uvPJzc1NTZs2VXR0tG7duiVJio2N1e7du/X444+rSJEiaWLw8vJS/fr1tXfv3nRjp1Ytrl69es84svM5pHriiSf06KOPatWqVbpw4UKm/Xbs2CFvb2/1798/TXvjxo316KOPav/+/YqJiUk3tr+/f4bj+fn56amnnko3lmEY6tOnT5rrTK1ateTt7Z3u315Orz05dfnyZT3//PPy8PDQggULrO/nN998o+joaHXt2lVxcXFpPsNHHnlEhQsXtp5Hqf/OU6eO/tXf73L2dyVKlMjW5w0g72OaFvA3zzzzjDp16qSkpCT99ttvWrBggS5fvixPT890fU+cOKFZs2Zp//791j+4Uv01iUjl5+eXbrFs6h9aN27csLalTgv7+9SPjNquXbumW7duZfiHj8Vi0YMPPqjdu3crJiYmzR9oFSpUSNe/ePHiGcaY+kf8X2O8lwcffNCaaP1d6h9+GcVcuHBhVaxY0foe/FXVqlXTtZ05c0aSslwsf+XKFUlShw4d9Nlnn+mDDz7Q0qVLVa9ePT388MN66qmnMv3D0ZE8PT3TvSedOnWSh4eHli1bppYtW6pp06aS/pxutGjRIm3YsEHnzp1Ldxvav34Wo0aN0rBhwxQWFiYfHx81atRITZs2VceOHa3TrlLfp/nz52v+/PkZxlexYkWbf7eMzqfU8+3GjRsqUqSIfvvtN6WkpGjz5s3avHlzhuNkNLUqNZHO6N+UvV599VWFhIRo2rRpmjFjRoZ9Lly4oAcffDDDhe7+/v46cOCAIiIi0iRjVapUyfSYGb3Pqf/GMtpWvHhxXb9+PU1bTq89OREbG6vnn39eN2/e1IoVK9J8tqnn0VtvvaW33norw/1T/72l/hvO6A56ZcqUyXJKoGEYufJ5A3A9JCPA31SsWNH6B+Pjjz+u5s2bq0uXLho5cqQ+/PBD638gL1++rD59+sjLy0uDBw9WtWrVVLhwYbm5uWn+/Pnav39/urELFCiQ6XH/XrnIbZnF4kox/l1GCWHqH+nz58/P9DalqX/gubu7a+HChfr555/19ddf64cfftCyZcs0f/58vfrqq/rHP/5hc2ylSpWSpHR/NGbHE088obVr12rfvn3WZGTSpElatmyZ2rVrp+eff16lS5dWoUKFFBkZqTFjxqT5LAIDA7Vz50598803OnDggL7//ntt375ds2bN0sqVK1W9enVr/9QbKWTEnrtKZee8Sf3f9u3bq0ePHtkeOzXxKl269D375vRzSF0k/tlnn9n1+f/d39c7/VVW71VW61xS2XLtya7ExEQNGzZMZ86c0dy5c9NVNFL/vY0cOVL16tXLcIzUxMoeN27cyNbnDSDvIxkB7qF69ep69tlntXDhQn322WfWqVA7duzQrVu3NGfOHOsfkKneffddu45ZqVIlSdLp06fT/Qf/9OnTaX4uVaqUihQpolOnTqUbxzAMnT59WsWLF3epW8amJgcZxRwfH68LFy6ocuXK2RqrSpUq2rt3r3x9fVWnTp1s7VOnTh1r35iYGPXq1UvTp09X37595e7ubtM3sg888IC8vb3T3XEtO+7evStJae4itnHjRj388MPpnrXw1VdfZThG4cKFFRQUZF3gvWfPHj3//PNasGCBJk6cmOab+swqVrmtUqVKcnNzU3x8fI5iSJ2ilJ3qlS2fw8iRI7Vjxw5NmjTJOg3u73GfP39eiYmJ6RLeU6dOyWKxZFgZyi25de0xDENjx47VgQMH9O9//1tPPPFEuj6p1UkPD497foap17HUaspfRUZGKjY2NsP9EhISdPny5WzfyhlA3saaESAbBg4cKC8vL7333ntKSkqSlPm3m1999VWa+fy2aNu2rSTpgw8+SPMN+IULF9JNb3Fzc1Pr1q119uxZhYeHp9m2adMmnT9/Xm3atHGpKQ+lSpXSww8/rK+//jrde7V48WLdvn3b+h7cS+r0rOnTp1v/qP+r2NhYJSYmSlKGt68tXry4KlasqLt371qnu6TOx//7OoCsFChQQA8//LCOHDmS4e1ss7J9+3ZJSpNMubm5patE3b17Vx988EG6/TP6vVK/0U6tKtSqVUv+/v5at25dhn8cGoaRrdv72qNkyZJ64okn9NVXX2X67X3qFJ+/OnTokNzc3PTII4/c8xi2fA4VKlRQ3759dfDgQe3evTvd9jZt2ig2NlYrVqxI037w4EHt379fTZo0cWqyn1vXnqlTp+qzzz7TkCFDMq1cNW/eXD4+Plq0aFGGt/tOSkqynnOlSpVSo0aNtHfvXv38889p+r3//vuZxnHs2DHdvXvXekt1APkblREgG0qWLKm+ffvqgw8+0MaNGxUSEqLHH39cXl5eeuWVVxQaGqqSJUvql19+0ebNm+Xv76+TJ0/afLymTZuqXbt22r59u5577jkFBQUpJiZGq1atUvXq1dP9h/3//u//9M0332jUqFE6cOCA/P39rbf2feCBBzRy5Eh73wKHGz9+vEJDQ9WvXz/16tVLFStW1A8//KDPPvtMNWvWTLdYODMBAQF6+eWXNWPGDHXs2FEdO3ZU2bJldfXqVZ08eVK7du3Sli1bVKFCBc2dO1d79+5Vy5YtVaFCBRUoUEDff/+9vvrqK7Vs2dK6fufBBx9UkSJF9NFHH8nT01PFihVTqVKl0n0L/Xft27fXl19+qe+++y7Dvrdv39ann35q/fn69ev66quv9M0336hOnTpp1r0EBwdr1apVeumll9SsWTPFxMRo8+bNGU6lat++vQIDA1WvXj2VKVNGMTEx1mfGpD5h3GKxaMqUKerXr5+6du2qrl27yt/fX0lJSfrjjz/0+eefq2vXrnrxxRez9b7b6q233lLv3r31j3/8Qx07dlRAQIDc3Nz0xx9/aM+ePapbt64mTpxo7Z+SkqI9e/aoefPm2b7t8L0+h4wMGTJEn3zySYbP/BkwYIB27NihyZMn68SJE2rQoIH11r5FixbV+PHjs/fLO0huXHv27NmjhQsXqmLFiqpWrVqa81T68wYXzZo1U+HChTV58mS98MIL6tChg5555hlVq1ZNt27d0vnz57Vz506NGjXK+sDJsWPHqm/fvgoLC1NoaKjKli2rffv26fjx45neTvnLL79UwYIF1aZNm5y/OQDyHJIRIJv69++vlStX6v3339fTTz+tihUrauHChXr33Xe1cOFCGYahgIAALVy4UGvXrrUrGZH+/JayWrVq2rhxoyZPnqwKFSpo2LBhKly4sMaOHZumb9myZbVu3TrNnj1bO3fu1Mcff6xSpUqpW7duevHFF+/5jAwz1KpVS2vXrtXs2bO1YcMGxcXFyc/PT/3797f+ntk1dOhQ1a1bVytWrNDKlSt169YtlSxZUlWrVtXLL78sX19fSVLr1q115coVbd++XVevXlXBggVVvnx5jR49Os3zDDw9PfXuu+9qxowZeuedd5SYmKjGjRvf8w/bDh06aNKkSdqwYUOGfa9cuaJXX33V+rOHh4cqVqyoF154QQMHDkwzBWjMmDHy9vbW1q1btXv3bvn5+aljx47q3LmzOnTokGbcAQMGaO/evfroo4908+ZNlShRQjVr1tTYsWPTTDuqWbOmPv30U33wwQfas2ePPvnkExUuXFhly5ZVUFCQ2rdvn+333FZlypTRhg0btHDhQn3++efatm2bChUqpDJlyujhhx9WSEhImv7ffvutIiMjM10snZF7fQ4ZKV68uIYOHZomEUrl7e2tjz76SHPmzLHG7O3traCgIL344osZ3lghN+XGtSe1InXhwoU052iqxo0bW8+lZs2aaf369VqwYIHCw8N19epVeXt7q1y5curWrVua9zwgIEArVqzQ1KlTtWLFChUsWFBNmzbVihUr0t21T/oz+dy0aZOCgoJ4+jpwn7AYZq9IBYB8ZOnSpZo2bZp27txpfSgjbDdgwADFxMRo7dq1OZpqyOeQN23ZskWvvPKK1q9fr5o1a5odDgAnYM0IADhQaGioypcvn+WceGTPwYMH9fXXX2vcuHE5XvPE55D3JCcna9asWQoJCSERAe4jVEYAAACA+8ytW7e0aNEiHT16VEePHtX169c1atQoDRo0KFv737x5U1OnTtWOHTsUHx+vgIAAvfrqqwoICMhRHFRGAAAAgPvM9evXNWfOHJ08eVK1a9fO0b4pKSkaNGiQNm/erNDQUL3yyiu6fv26nn322Qzv2JgVFrADAAAA9xk/Pz/t2bNHZcqUUUREhPU5VdkRHh6un376Se+++671pirt27dXu3btNGvWLM2cOTPbY1EZAQAAAO4z7u7uNt+1bvv27SpZsqSCg4OtbaVKlVL79u31xRdfKD4+PttjkYwAAAAAyLbjx4+rdu3acnNLm0oEBAQoISFBZ8+ezfZYTNMCAAAA8qB7Ta3atWtXrhw3OjpaDRo0SNfu5+cnSYqKisr2OhSSEUlt3LrbPYZbDh7QlpmUO3fsHgOAedZG7HfION0rNHHIOACQn+xMWWt2CJlKuexv0pErmnLU+Pj4NA/qTZXalpNpWiQjAAAAQB6UW5WPe/H09FRiYmK69tQ2T0/PbI/FmhEAAAAA2ebr66vo6Oh07VFRUZL+N10rO6iMAAAAAHZIUYopxzWrqlCzZk199913SklJSbOI/ciRI/Lw8FC1atWyPRaVEQAAAAAZioqK0pkzZ3T37l1rW3BwsK5fv67w8HBr27Vr1xQeHq4nn3wyR9O0qIwAAAAAdkg2zKmM2PuH/MqVK3Xz5k3FxsZKkg4cOKCkpCRJUlhYmIoWLarp06drw4YN2rVrlypUqCBJateunerXr69x48bp7NmzKlmypFatWqWkpCSNGDHCqb9Drrl48aJ++eUXRUVFKSEhQR4eHvLz81OtWrVUvnx5s8MDAAAA8rTFixfrjz/+sP789ddf6+uvv5YkPf300ypatGiG+xUoUEAffPCBpkyZohUrVig+Pl4BAQF65513VL169RzFYDEMw7D9V3C8gwcPavLkyTp69KgyCs1isahu3bp69dVX9cgjjzjkmNzaF4AjcGtfAMg9rnxr3zuXqppy3MIP/GbKcR3JpSojX3/9tQYPHqzy5ctr5MiRCggIkJ+fn9zd3ZWYmKioqCgdPnxYGzZsUP/+/TVv3jw1b97c7LABAAAA2MClKiPdu3dXoUKFtHTp0gwfpJIqMTFR/fr10927d7Vu3Tq7j0tlBIAjUBkBgNxDZSS9/FAZcam7aZ08eVJdu3bNMhGR/ny6Y9euXXXq1CknRQYAAABkLMWk/8sPXCoZKV68uM6dO5etvufOnVPx4sVzNyAAAAAAucal1ow8/fTTWrp0qUqVKqUePXpkuII/NjZWa9as0fLly/Xcc885P0gAAADgL5JdZ9VDnuNSychLL72kixcvasqUKZo+fboqVqwoX19f6wL26OhoXbhwQcnJyQoODtZLL71kdsgAAAAAbORSyYi7u7umT5+u5557TuHh4Tpx4oSio6MVHx8vT09PlStXTq1atVJwcLDq1atndrgAAAAA7OBSyUiqevXqkWwAAAAgT0gR07Rs5VIL2AEAAADcP1yyMpIXbTy91+4xni7/sAMiAWCWHlVaOGikuw4aBwDgDMlURmxGZQQAAACAKUhGAAAAAJiCaVoAAACAHVjAbjsqIwAAAABMQWUEAAAAsANPYLcdlREAAAAApqAyAgAAANghxewA8jAqIwAAAABMQTICAAAAwBRM0wIAAADswBPYbUdlBAAAAIApqIwAAAAAdkimMGIzKiMAAAAATEEyAgAAAMAUTNMCAAAA7MBzRmxHZQQAAACAKaiMOMjT5R+2e4w/XnvM7jHKv/ON3WMAsM3ppXUdMk71vj85ZBwAgHMky2J2CHkWlREAAAAApqAyAgAAANghhVv72ozKCAAAAABTkIwAAAAAMAXTtAAAAAA7sIDddlRGAAAAAJjC5ZKRU6dOadSoUerSpYv69++vdevWyTDSrwratGmTatWqZUKEAAAAwP8ky2LKKz9wqWTk3Llz6tGjh3bu3Ck3NzedPXtW48ePV58+fRQdHW12eAAAAAAcyKWSkRkzZqhIkSLavHmz1q9fr6+++kqTJk3SqVOn1LNnT509e9bsEAEAAAA4iEslI4cPH1bfvn1VuXJla1vnzp21Zs0aubm5qU+fPjpy5IiJEQIAAABppRgWU175gUslIzdu3JCPj0+69urVq2v16tUqW7as+vXrp71795oQHQAAAABHcqlkpHz58vr1118z3Obj46OVK1eqdu3aGjp0qMLDw50cHQAAAJAeC9ht51LJSOPGjRUeHq6kpKQMt3t7e2vJkiVq0aKFdu/e7eToAAAAADiSSz30sGvXrrpy5YqOHTum+vXrZ9jH3d1dc+bM0YQJE3TixAnnBggAAAD8TbJrfb+fp7hUMhIQEKBZs2bds5+bm5vGjRvnhIgAAAAA5BbSOAAAAACmcKnKCAAAAJDX5Jfb7JqBZMSFlH/nG7vHODOjiQMikaq/vN8h4wD3lSseZkcAAECeQjICAAAA2CG/3GbXDKwZAQAAAGAKkhEAAAAApmCaFgAAAGCHZIPv923FOwcAAADAFFRGAAAAADuk8P2+zXjnAAAAAJiCyggAAABgB27tazsqIwAAAABMQTICAAAAwBRM0wIAAADswK19bcc7BwAAAMAUVEYAAAAAO6SwgN1mVEYAAAAAmIJkBAAAAIApmKYFAAAA2CGZ7/dtRjKSz1R/eb9DxnFzd7d7jJTERAdEAuQdR7vPcsg4XV5u7JBxAABwdSQjAAAAgB24ta/teOcAAAAAmILKCAAAAGCHFL7ftxnvHAAAAABT5Jlk5Nq1axoyZIiOHDlidigAAAAAHCDPJCN37tzRl19+qStXrpgdCgAAAGCVbFhMeeUHLrNmJDAwMMvthmFIkkaMGCE3NzdZLBYdOnTICZEBAAAAyA0uk4wkJCTIy8tLQUFBKlgwfVi3bt3Sjh071LBhQ5UrV86ECAEAAID0eOih7VwmGZk8ebKmTp2qn3/+WWPGjNHjjz+eZntERIR27NihZ599VkFBQSZFCQAAAMBRXCaNe/rppxUeHq5WrVpp2LBhGjRokM6ePWvdbrHkj3lxAAAAAP7kMsmIJHl5eWn06NHavHmzpD8TlP/+97+6efOmyZEBAAAAGUsx3Ex55Qcu+VtUqVJFH3zwgd577z3t2bNHbdq00erVq6mOAAAAAPmIy6wZyciTTz6pZs2aacmSJZo3b571jloAAACAq2ABu+1cOhmRpEKFCmnQoEHq06ePYmJiVLp0abNDAgAAAOAALp+MpPL29pa3t7fZYQAAAABp5JcHEJqBmhIAAAAAU+SZygicKyUx0ewQgDynsMXD7BAAAMhTSEYAAAAAO6Qw2chmvHMAAAAATEFlBAAAALBDcj55AKEZeOcAAAAAmIJkBAAAAIApmKYFAAAA2CFFPGfEVlRGAAAAAJiCyggAAABgBxaw2453DgAAAIApSEYAAAAAmIJpWgAAAIAdkvl+32a8cwAAAABMQWUEAAAAsEOKwa19bUVlBAAAAIApqIwAAAAAdmDNiO145wAAAACYgsoIXNr2i4ftHqNduUAHRALcG+caAAA5QzICAAAA2CGFJ7DbjHcOAAAAgCmojAAAAAB2SBa39rUVlREAAAAApiAZAQAAAGCKPDFN69dff9WPP/6omzdvqlSpUmrSpIkqVqxodlgAAAAAC9jt4FLJyKJFi3Tp0iWNHz9ekhQfH6/Ro0dr165dMgzD2q9AgQIKDQ3Va6+9ZlaoAAAAAOzkUsnI+vXr1bp1a+vP//3vf7Vr1y7169dPnTp1ko+Pjy5fvqw1a9ZoxYoVKlOmjAYMGGBixAAAALjfsYDddi6VjPzxxx+qUKGCJMkwDH322Wd67rnn9M9//tPap0yZMgoMDFRCQoLWrFlDMgIAAADkUS6VjHh4eOj27duSpDt37ujOnTtq1KhRhn0ffvhh7dixw5nhAQAAAOmwZsR2LvXONWzYUNu2bZMkeXl5qUqVKvruu+8y7HvgwAH5+fk5MzwAAAAADuRSlZEXX3xRPXv21EsvvaSRI0fqjTfe0AsvvKCkpCR16NBBPj4+ioyM1Lp167R9+3a9+OKLZocMAAAAwEYulYzUrl1bc+fO1ZgxY9ShQwd5e3tLklatWqVVq1ZZ+xmGoW7dumnw4MFmhQoAAABIkpKZpmUzl0pGJKl58+YKDw/X5s2b9e233+r333/X7du35enpKT8/P9WpU0ft27dXrVq1zA4VAAAAgB1cLhmRJG9vb/Xu3Vu9e/c2OxQAAAAgSyl59Na+iYmJmjVrlj799FPFxMTI399fI0aMUIsWLe6577Fjx/Tee+/p2LFjunXrlsqVK6fOnTurX79+8vDwyHYM1JQAAACA+9CYMWO0ZMkSdezYUePGjVPBggU1ePDgTG8glerYsWPq1auXLly4oH/84x/65z//KX9/f02bNk1jxozJUQwuWRkBUrUrF2j3GNsvHnZAJI6JBQAAwBUcOXJEW7Zs0ahRozRo0CBJUpcuXdSxY0dNnjxZ69aty3TfNWvWSJJWrlypkiVLSpJ69eqlu3fvKjw8XP/973/l5eWVrTiojAAAAAB2SDbcTHnZIzw8XG5uburZs6e1zcPDQyEhITp69KgiIiIy3Tc2Nlbu7u4qXrx4mnZfX18VKFBAhQoVynYcVEYAAACAPCgoKCjL7bt27cp02/Hjx1WpUqV0CUW9evWs2ytUqJDhvo888oi2bdumcePGacCAAfLy8tKBAwe0fv16DRgwgGQEAAAAcJYUI+8tYI+Ojpavr2+69tS2qKioTPft2bOnTp8+rY8//ljr16+XJFksFo0cOTLHj94gGQEAAADyoKwqH/cSHx8vd3f3dO2pd8KKj4/PdN+CBQuqcuXKatKkifXZgLt379a7774rb29vhYaGZjsOkhEAAADADsl5cBm2p6enEhMT07UnJCRYt2fmgw8+0JIlS7Rjxw4VLVpUktSuXTsZhqHJkyerffv2KlWqVLbiyHvvHAAAAAC7+Pr6Kjo6Ol17apufn1+m+3700Ud69NFHrYlIqtatWys+Pl7Hjh3LdhwkIwAAAMB9pmbNmjp//rxiYmLStB8+fNi6PTNXrlxRcnJyuvakpCRJynBbZkhGAAAAADukGBZTXvYIDg5WSkqK9Zkh0p9PZF+/fr3q1KmjihUrSvpzIfuZM2d09+5da7+qVatq//79unLlSpoxN2/eLDc3N9WuXTvbcbBmBAAAALjPBAYGKjg4WDNnztT169dVpUoVbdy4UREREVq8eLG13/Tp07Vhwwbt2rXLeqvfwYMHa9SoUerevbt69eolb29v7dq1S/v27VPPnj1VpkyZbMdBMgIAAADYISWPTjaaPHmyZs6cqU2bNikmJkYPPfSQ5s6dqyZNmmS5X8eOHVW6dGnNmzdPy5Yt082bN1WxYkWNGjVKAwYMyFEMFsMwDHt+ifygjVt3s0NALtp+8bBDxmlXLtAh4wAAgJzbmbLW7BAyNfpwz3t3ygVTA9fcu5OLy5tpHAAAAIA8j2laAAAAgB2S8+AT2F0FlREAAAAApqAyAgAAANjB3tvs3s+ojAAAAAAwBZUR5HuOugvWmRlZ3+YuO6q/vN8BkcBVOeIckThPACCvSTH4ft9WvHMAAAAATEEyAgAAAMAUTNMCAAAA7JAsFrDbisoIAAAAAFNQGQEAAADswK19beeSycjZs2dVuHBhPfDAA9a2U6dO6ccff1RSUpLq1q2rwEDH3CEJAAAAgDlcKhmJjY3V888/r8OHD0uSnn76aU2aNElTpkzRkiVLlJKSIkmyWCxq3ry55syZI3d3dzNDBgAAAGAjl0pGFixYoKNHj6pfv37y8fHR4sWL9e9//1urV6/WkCFD1Lp1ayUlJWnTpk1auXKl5syZo5EjR5odNgAAAO5jPGfEdi6VjGzfvl0hISEaM2aMJKly5cp68cUX1a9fP7300kvWfvXq1VN0dLS2bNlCMgIAAADkUS6VxkVGRqpu3brWn+vVqydJaty4cbq+TZs2VWRkpNNiAwAAADKSIospr/zApZKREiVK6Pr169afr169Kkm6cuVKur5XrlxR6dKlnRYbAAAAAMdyqWSkYcOGWr16tU6fPq0bN25o1qxZ8vT01Pbt23Xx4kVrvzNnzmjlypWqVauWidECAAAAUrJhMeWVH7jUmpERI0YoJCREnTp1kiQZhqEXX3xRFStWVHBwsGrVqqWkpCT9+uuvkqQXX3zRzHABAAAA2MGlkpHKlStr8+bN2rhxo+Li4vTII4/oiSeekCQVKFBAq1atUkxMjFq0aKEBAwaodu3aJkcMAAAAwFYulYxIUtmyZTVkyJB07U899ZSeeuopEyICAAAAMsetfW3HOwcAAADAFC5XGQFcVfWX99s9Rrn9xewe42KTm3aPgdxR7ivD7BAAACZIySeLyc1AZQQAAACAKUhGAAAAAJiCaVoAAACAHfLL09DNQGUEAAAAgCmojAAAAAB2YAG77aiMAAAAADAFlREAAADADjz00Ha8cwAAAABMQTICAAAAwBRM0wIAAADswAJ221EZAQAAAGAKKiMAAACAHXjooe2ojAAAAAAwBckIAAAAAFMwTQsAAACwAwvYbUdlBAAAAIApqIwATnSxyU2zQ0Au2jPnA4eM025DoEPGAQA4B5UR21EZAQAAAGAKl09G4uPjdePGDcXHx5sdCgAAAAAHcrlpWomJifrkk0+0bds2HT9+XHFxcdZt3t7eqlmzptq3b6+QkBC5u7ubGCkAAADANC17uFQycvXqVfXv318nT55UlSpV1LJlS/n6+srDw0MJCQmKjo7WkSNH9Pbbb2vVqlVaunSpSpcubXbYAAAAAGzgUsnIhAkTFBkZqSVLlqhp06aZ9vv222/18ssva+LEiZoyZYoTIwQAAADSojJiO5daM7J3714NGDAgy0REkpo2baoBAwZoz549TooMAAAAgKO5VGXk7t27KlKkSLb6Fi5cWHfv3s3liAAAAICspYjKiK1cqjLSsGFDLVu2TJcvX86y36VLl7R8+XI1atTISZEBAAAAcDSXqoyMHTtWoaGhateunZ544gnVrVtXvr6+cnd3V2JioqKjo3Xs2DF99dVX8vLy0pgxY8wOGQAAAICNXCoZqV69uj799FPNnTtXO3fu1I4dO9L1KVWqlLp27aohQ4aobNmyJkQJAAAA/A8L2G3nUsmIJJUpU0Zvvvmm3nzzTUVGRio6Olrx8fHy9PSUr6+vypQpY3aIAAAAABzA5ZKRvypTpkymyUdcXJxu3rypcuXKOTkqAAAA4H+ojNjOpRaw58SKFSsUFBRkdhgAAAAAbJRnkxEAAAAAeZtLTdNasGBBtvsePHgwFyMBAAAAsodpWrZzqWRk2rRpslgsMgwjW/0tFj54AAAAIK9yqWSkZMmSql27tt5+++179l25cqWWLl2a+0EBcHkpTzS0ewy3r360e4zhFxvbPcafEhw0DvKrAkWLOmSc5NhYh4wD3O+ojNjOpZKRgIAAnTp1SuXLl79n32LFijkhIgAAAAC5xaUWsNetW1eXLl1SdHT0PfsWK1ZMDzzwgBOiAgAAADJnGBZTXvmBSyUjAwcO1K5du1SiRIl79g0NDdXu3btzPygAAAAAucKlpml5eXnJy8vL7DAAAAAAOIFLJSMAAABAXpOi/DFlygwuNU0LAAAAwP2DyggAAABgB27tazsqIwAAAABMQTICAAAAwBRM0wIAAADskF+e+WEGKiMAAAAATEFlBAAAALADC9htR2UEAAAAgCmojAAAAAB2YM2I7aiMAAAAADAFyQgAAAAAUzBNCwAAALADC9htRzICwCYFazzokHGSfj1t9xhuX/3ogEjs17HkIYeM865qOWQc5F/JsbFmhwAADkEyAgAAANjBMMyOIO9yyTUj+/bt07Jly7Rp0ybFxMRk2OfQoUMaO3askyMDAAAA4CguVRlJTEzUwIED9f3338v4/ymmt7e3Ro8erV69eqXpe/78eW3cuFETJkwwI1QAAAAAdnKpZGTRokU6ePCghg8frjZt2ig6OloLFy7UW2+9pV9++UVvvvmm3NxcspgDAACA+1SKWMBuK5dKRrZu3aquXbtq2LBhkiR/f381a9ZM8+bN08yZM3XlyhXNmDFD7u7uJkcKAAAAwF4uVWaIiIhQ/fr107UPGTJE06ZN0969e9W/f3/FchcRAAAAuAjDsJjyyg9cKhkpXry4rl27luG2Dh06aN68efrll18UGhqqqKgoJ0cHAAAAwJFcKhmpVauWvvjii0y3N2vWTEuXLlVUVJTeffddJ0YGAAAAZCzFsJjyyg9cKhlp06aNDh06pEOHDmXaJzAwUB9++KF8fX2dFxgAAAAAh3OpBexdu3ZVcHCwChUqlGW/6tWra8uWLbpx44ZzAgMAAADgcC6VjFgsFnl5eWWrr2EYsljyR3kKAAAAeRdPYLedS03TyokVK1YoKCjI7DAAAAAA2MilKiMAAABAXpNfbrNrBpdKRhYsWJDtvgcPHszFSAAAAADkNpdKRqZNmyaLxSIjmxPvWDMCAAAA5F0ulYyULFlStWvX1ttvv33PvitXrtTSpUtzPygAAAAgC0zTsp1LJSMBAQE6deqUypcvf8++xYoVc0JEyA/OzGjikHGqv7zfIePkF0m/njY7BJczfHN/h4xTXZxrAID7g0vdTatu3bq6dOmSoqOj79m3WLFieuCBB5wQFQAAAJA5nsBuO5dKRgYOHKhdu3apRIkS9+wbGhqq3bt3535QAAAAAHKFS03T8vLyyvZDDwEAAABXwEMPbedSlREAAAAA9w+SEQAAAACmcKlpWgAAAEBew619bUdlBAAAAIApqIwAAAAAdqAyYjsqIwAAAABMQTICAAAAwBRM0wIAAADswGNGbEdlBAAAAIApqIwAAAAAdmABu+2ojAAAAAAwBZURAAAAwB4sGrEZlREAAAAApqAygnyv+sv7zQ4BuWz7xcN2j9GuXKDdY3CuAQCQM3mqMhIfH68dO3YoOjra7FAAAAAASX8uYDfjZa/ExERNnTpVLVq0UL169RQSEqK9e/dme/9vv/1Wzz33nBo1aqQGDRqoS5cu2rBhQ45iyFPJyNWrVzVixAgdPXrU7FAAAACAPG3MmDFasmSJOnbsqHHjxqlgwYIaPHiwvvvuu3vu+8knn6h///4qUKCARo4cqX/+859q0qSJLl68mKMYXGqa1ptvvpnl9lu3bskwDK1atUp79uyRxWLRG2+84ZzgAAAAgAwYeXAB+5EjR7RlyxaNGjVKgwYNkiR16dJFHTt21OTJk7Vu3bpM942IiNDbb7+tvn37avz48XbF4VLJyOrVq2WxWGRk8YlaLBZr+YhkBAAAAMi58PBwubm5qWfPntY2Dw8PhYSEaPr06YqIiFCFChUy3Hf16tVKTk7WiBEjJElxcXEqUqSILJacTx1zqWlaTZs2laenp0aMGKEjR47oxIkTaV6ff/65DMPQnDlzdOLECR0/ftzskAEAAIA85/jx46pUqZKKFy+epr1evXrW7Zn55ptvVK1aNX311Vd64okn1KhRIzVu3FhTp05VcnJyjuJwqcrIkiVLtGPHDk2aNElr167VK6+8ovbt21u325JtAQAAALnJrCewBwUFZbl9165dmW6Ljo6Wr69vuvbUtqioqEz3/f3331WgQAGNHTtWAwcOVK1atbR7924tWLBACQkJGjduXDZ/AxerjEhS27ZttW3bNj3zzDMaO3as+vTpo59//tnssAAAAIB8Iz4+Xu7u7unaPTw8rNszc/v2bcXExOjFF1/UiBEj1LZtW02cOFFt2rTRqlWrdO3atWzH4VKVkVTu7u4aPny4nnnmGU2cOFHdu3dX586d08xpAwAAAFyCSZWRrCof9+Lp6anExMR07QkJCdbtWe17+/ZtdezYMU17p06dtHPnTh09elRPPPFEtuJwucrIX5UrV06zZs3S4sWLdezYMYWFhTFVCwAAALCTr69vhs/uS23z8/PLdN/UbT4+PmnaS5cuLUmKiYnJdhwuWRn5uyZNmmjjxo3asGGDLl++rGrVqpkdEgAAAJBn1axZU/v371dMTEyaReyHDx+2bs9MnTp1dO7cOUVGRqpixYrW9sjISElSqVKlsh2HS1dG/qpAgQIKCQnR8OHDVbVqVcXFxeX4oSoAAACAoxmGOS97BAcHKyUlRWvWrLG2JSYmav369apTp441yYiKitKZM2d09+5da78OHTpIUppnkRiGoXXr1snLy0v169fPdhx5ojKSkRUrVmjWrFnc3hcAAADIocDAQAUHB2vmzJm6fv26qlSpoo0bNyoiIkKLFy+29ps+fbo2bNigXbt2WZ87EhQUpKZNm2r+/Pm6fv26atSooS+//FLffPONxowZI29v72zHkWeTEQAAAMAl5MEnsEvS5MmTNXPmTG3atEkxMTF66KGHNHfuXDVp0iTL/SwWi+bMmaOZM2dq69atWr9+vSpXrqz//ve/CgkJyVEMFiOrx5072YIFC7Ldd//+/frmm28cUhlp49bd7jEAmGf7xcN2j9GuXKADIgEA5JadKWvNDiFT1T56x5Tjnu3zminHdSSXqoxMmzZNFotF2c2PuLMWAAAAzGbWQw/zA5dKRkqWLKnatWvr7bffvmfflStXaunSpbkfFAAAAIBc4VLJSEBAgE6dOqXy5cvfs2+xYsWcEBHyA0uBAg4Zx0hOdsg4cDxHTLH67I8f7B6jY/lGdo8BAMD9xKVu7Vu3bl1dunQpwwew/F2xYsX0wAMPOCEqAAAAIAuGSa98wKWSkYEDB2rXrl0qUaLEPfuGhoZq9+7duR8UAAAAgFzhUtO0vLy85OXlZXYYAAAAQLaxgN12LlUZAQAAAHD/IBkBAAAAYAqXmqYFAAAA5Dn5ZDG5GaiMAAAAADAFlREAAADALixgtxWVEQAAAACmoDICAAAA2IM1IzajMgIAAADAFCQjAAAAAEzBNC0AAADAHkzTshmVEQAAAACmoDICAAAA2MPg1r62ojICAAAAwBRURpDvGcnJZoeAPKBj+UZ2j7Ht4k8OiERqX66BQ8ZBPmZx0HeJRopjxgEAG+WZZOTOnTuKjY1ViRIl5O7ubnY4AAAAgCTJYAG7zVwqGTl69KiuXLmili1bWts+//xzvf/++zpx4oQMw1CBAgXUsGFDjR49WvXq1TMxWgAAAAD2cKk1I5MnT9bnn39u/Xnz5s0aPny4rly5oj59+uill17SM888o5MnT6pv3746dOiQecECAAAA0p+39jXjlQ+4VGXk5MmTatu2rfXnd999Vw0bNtSSJUvk4eFhbR89erR69+6t6dOna/ny5WaECgAAAMBOLlUZSUhIUOHChSVJt2/f1sWLF9W3b980iYgkFStWTD169NDRo0fNCBMAAAD4H8NizisfcKlkpGrVqvrppz/vRlO4cGF5eXkpNjY2w76xsbEqVKiQM8MDAAAA4EAulYz07NlTn376qXbt2iWLxaKwsDDNnj07XQXk22+/1dKlS9WkSROTIgUAAABgL5daM9KrVy8dPnxYw4YNU2BgoAICApSUlKQePXqoQoUKKl26tKKionTp0iX5+Pjo1VdfNTtkAAAA3Ocs+WQxuRmylYw8++yzOR7YYrFo2bJlOd5vwoQJatGihZYtW6YPP/xQxv+/cfOFCxd04cIF+fj4KCwsTIMHD1bp0qVzPD4AAAAA15CtZCQiIiK340ijQ4cO6tChg+Li4nThwgXdunVLnp6e8vPzk5+fn1NjAQAAALJEZcRm2UpGdu/endtxZMjb21u1atXKcFtcXJxu3rypcuXKOTkqAAAAAI7gUgvYc2LFihUKCgoyOwwAAAAANnKpBewAAABAnpNPnvlhBpuTkZs3b2rdunU6fPiwYmJilJKSkma7LQvYFyxYkO2+Bw8ezNHYAAAAAFyLTcnIpUuX1Lt3b12+fFlFixZVXFycihcvrps3byolJUUlS5a0Pkk9J6ZNmyaLxWK9g9a9WCxkoQAAADAZC9htZlMyMnPmTN24cUNLlixRjRo19Nhjj+ndd99V/fr1NWfOHIWHh+vDDz/M8bglS5ZU7dq19fbbb9+z78qVK7V06VIbogcAAADgCmxKRr755huFhISoadOmun79urW9cOHCGj16tE6dOqVp06Zp8uTJORo3ICBAp06dUvny5e/Zt1ixYjmOGwByU/tyDRwyzvaLh+0eo125QAdEApdlpNy7DwDnoTJiM5vupnXt2jXVqFFDklSw4J/5TEJCgnV78+bNtW/fvhyPW7duXV26dEnR0dH37FusWDE98MADOT4GAAAAANdgUzJSokQJxcbGSvrzWSCFChXSxYsXrdstFotu3bqV43EHDhyoXbt2qUSJEvfsGxoaatrzTwAAAADYz6ZkpGrVqjp9+rSkPxOPOnXqaMOGDUpMTNSdO3e0fv16VapUKcfjenl5qXz58ipUqJAtYQEAAADOZ5j0ygdsSkaaNWumHTt2WKdmDRw4UEePHlXjxo312GOP6fjx43ruueccGScAAACAfMamBeyDBw/WP/7xD7m7u0uSWrdurffee0+ffvqp3NzcFBwcrPbt2zs0UAAAAMAl8dBDm9mUjFgsFmsikqp169Zq3bq1Q4ICAAAAkP/ZNE0LAAAAAOxlU2Xkvffeu2cfi8WiYcOG2TI8AAAAkGdY8slicjM4PBmxWCwyDINkBAAAAECWbEpGdu3ala4tOTlZ58+f15IlS3Tr1i1NnDjR7uAAAAAAl0dlxGY2JSPly5fPsL1SpUpq1qyZevXqpY0bN+rll1+2JzYAAAAA+ZjDF7BbLBa1b99eGzdudPTQAAAAAPKRXLub1tWrV3NraAAAAAD5gMOTkaioKK1evVqVK1d29NAAAAAA8hGb1ow8++yzGbbHxMTo7Nmzunv3rqZNm2ZXYAAAAEBewK19bWdTMhIREZGuzWKxqHjx4mrbtq2effZZBQYG2h0cAAAAgPzLpmRk9+7djo4DAPD/tStn/5c52y8edok4AOC+YFjMjiDPsmnNyMWLFxUfH5/p9vj4eF28eNHmoAAAAADkfzYlI0FBQdq5c2em23fv3q2goCCbg8pMYmKi7ty54/BxAQAAADifTcmIYWS9SiclJUUWi23lqjVr1qhnz57q16+fvv76a0nSkSNH1L17d9WvX18NGzZUhw4dtHXrVpvGBwAAABzKMOmVD9h8a9+sko0zZ86oaNGiOR5z27ZteuONN3Tx4kVdvXpVQ4cO1b59+9S/f3/dvHlTffr0Ua9evXTr1i2NGjWKtSsAAABAHpbtBewbNmzQhg0brD/PnTtXH3/8cbp+MTExOnXqlFq3bp3jYJYtW6bAwECtWLFC7u7umjJlil5++WXVqFFDy5YtU6FChSRJo0aNUvfu3bVgwQK1atUqx8cBAAAAHCafVCnMkO3KyM2bNxUREaGIiAhZLBZdu3bN+nPq648//lBKSoq6deumN998M8fB/Pbbb+rUqZPc3d0lST169FBsbKx69eplTUQkydvbWyEhITpx4kSOjwEAAADANWS7MtKvXz/169dPklSzZk299tpr6tSpk0ODSUlJUcGC/wupQIECkmRNTv7K3d09TV8AAADADDz00HY2rRnZtWuXTdOw7qVatWr64osv0hxHkj7//PM0/QzD0LZt21SpUiWHxwAAAADAOWwqLRQpUkS///67atasmeH2EydO6IEHHlDx4sVzNO5zzz2nkSNHqnv37ipdurT27t2rRx99VMWKFdPAgQPVunVrJScna8uWLfrpp59smgoGAAAAwDXYlIxMnTpVx44d08aNGzPcPnbsWNWrV09vvfVWjsZt3769rly5opUrV+rixYtq06aNXn/9dXl6euqll16yJh9ubm7q3r27evToYUv4AAAAgOMwTctmNiUj+/fvz3K9SKtWrbR582abAgoLC1NYWFi69oULF+rChQu6evWqKleurJIlS9o0PgAAAADXYFMyEhUVpXLlymW6vWzZsoqKirI5qMxUrFhRFStWlCTFxcXp5s2bWcYBAAAA5DoqIzazaQG7p6enLl++nOn2y5cv5/qdrlasWKGgoKBcPQYAAACA3GNTMlK7dm199tlnio+PT7ctISFBn332mWrVqmV3cAAAAADyL5vKF2FhYRo2bJj69++vUaNGWROP48ePa/r06Tp//rxGjx6d43EXLFiQ7b4HDx7M8fgAAACAo/GcEdvZlIwEBQVp6NChmjt3brrF5oZhaPDgwWrTpk2Ox502bZosFosMI3ufqMViyfExAAAAALgGmxd2jBgxQq1atdKmTZv0+++/S5KqVKmiTp06KSAgQIcPH1ZgYGCOxixZsqRq166tt99++559V65cqaVLl9oSOgDkioK+Pg4ZJyn6it1jtCuXs+tvRt4/v8/uMV6o1MzuMQDA5Rl8QW4ru1aZBwQEKCAgwPpzTEyMPv30U7322ms6ffq0jh8/nuPxTp06pfLly9+zb7FixXIcLwAAAADX4ZBbXh04cEBr167Vzp07lZCQoKJFi+rpp5/O8Th169bVnj17FB0dLV9f3yz7FitWTA888ICtIQMAAAAwmc3JyNWrV/XJJ5/ok08+0fnz5yVJzZs3V2hoqJo1a6ZChQrleMyBAweqW7duKlGixD37hoaGKjQ0NMfHAAAAAByKBew2y1EyYhiG9uzZo3Xr1umLL75QUlKSGjRooE6dOum9995T9+7d9eSTT9ocjJeXl7y8vGzeHwAAAEDeke1kZPbs2Vq/fr0uXbokX19fPffcc+rWrZuqVq2q8+fP67333svNOAEAAACXxK19bZftZGTOnDmqXLmy5s+frxYtWsjNzabnJQIAAACApBw8gb1UqVL6/fffNWHCBC1cuFCRkZG5GRcAAACQNxgmvfKBbCcje/bs0cyZM1W+fHnNmDFDrVq10qBBgxQeHq7ExMTcjBEAAABAPpTtaVoFCxZUu3bt1K5dO128eFFr167V+vXrNXLkSHl6espisVAtAQAAAJBtNi38KFeunEaMGKEvvvhC77//vpo0aSI3Nze98847atWqlSZNmqRDhw45OFQAAADA9VgMc175gV2r0N3c3NSyZUvNnTtXX3zxhV566SW5ublpyZIl6t27t6NiBAAAAJAPOeyWWH5+fho6dKg+//xzLVq0SO3atXPU0AAAAIDrYgG7zWx+AntWmjVrpmbNmuXG0AAAAADyCR4WAgAAAMAUuVIZAQAAAO4b+WTKlBmojAAAAAAwBZURAHCQpOgrZofgUC9Usn/t3/aLh+0eo125QLvHAIDclF9us2sGKiMAAAAATOHyyUh8fLxu3Lih+Ph4s0MBAAAA4EAuN00rMTFRn3zyibZt26bjx48rLi7Ous3b21s1a9ZU+/btFRISInd3dxMjBQAAAGAPl0pGrl69qv79++vkyZOqUqWKWrZsKV9fX3l4eCghIUHR0dE6cuSI3n77ba1atUpLly5V6dKlzQ4bAAAAgA1cKhmZMGGCIiMjtWTJEjVt2jTTft9++61efvllTZw4UVOmTHFihAAAAMDfsIDdZi61ZmTv3r0aMGBAlomIJDVt2lQDBgzQnj17nBQZAAAAAEdzqcrI3bt3VaRIkWz1LVy4sO7evZvLEQEAAABZ49a+tnOpykjDhg21bNkyXb58Oct+ly5d0vLly9WoUSMnRQYAAADA0VyqMjJ27FiFhoaqXbt2euKJJ1S3bl35+vrK3d1diYmJio6O1rFjx/TVV1/Jy8tLY8aMMTtkAAAAADZyqWSkevXq+vTTTzV37lzt3LlTO3bsSNenVKlS6tq1q4YMGaKyZcuaECUAAADwF0zTsplLJSOSVKZMGb355pt68803FRkZqejoaMXHx8vT01O+vr4qU6aM2SECAAAAcACXS0b+qkyZMiQfAAAAcG1URmzmUgvYJenUqVMaNWqUunTpov79+2vdunUyjPSf8KZNm1SrVi0TIgQAAADgCC6VjJw7d049evTQzp075ebmprNnz2r8+PHq06ePoqOjzQ4PAAAASMdimPPKD1wqGZkxY4aKFCmizZs3a/369frqq680adIknTp1Sj179tTZs2fNDhEAAACAg7hUMnL48GH17dtXlStXtrZ17txZa9askZubm/r06aMjR46YGCEAAAAAR3GpZOTGjRvy8fFJ1169enWtXr1aZcuWVb9+/bR3714TogMAAAAyYJj0ygdc6m5a5cuX16+//prhNh8fH61cuVKDBw/W0KFD9fjjjzs5OgDI2vaLhx0yTrtygQ4ZxxXkp98FAOB4LlUZady4scLDw5WUlJThdm9vby1ZskQtWrTQ7t27nRwdAAAAkB4L2G3nUslI165d1aBBAx07dizTPu7u7pozZ47CwsL08MMPOzE6AAAAAI7kUtO0AgICNGvWrHv2c3Nz07hx45wQEQAAAIDc4lKVEQAAACDPyaML2BMTEzV16lS1aNFC9erVU0hIiE03ipo7d65q1Kih4ODgHO9LMgIAAADch8aMGaMlS5aoY8eOGjdunAoWLKjBgwfru+++y/YYly9f1vz58+Xl5WVTDC41TQsAAADIc/LgYvIjR45oy5YtGjVqlAYNGiRJ6tKlizp27KjJkydr3bp12Rpn0qRJCgwMVEpKiqKjo3McB5URAAAA4D4THh4uNzc39ezZ09rm4eGhkJAQHT16VBEREfcc4/vvv9f27dv12muv2RwHyQgAAABgh7x4a9/jx4+rUqVKKl68eJr2evXqWbdnJTk5Wf/+978VEhKiGjVq2BwH07QAAACAPCgoKCjL7bt27cp0W3R0tHx9fdO1p7ZFRUVlOfbq1at18eJFLV269N6BZoHKCAAAAHCfiY+Pl7u7e7p2Dw8P6/bMXL9+XbNmzdILL7ygUqVK2RUHlREAAADAHiYtYM+q8nEvnp6eSkxMTNeekJBg3Z6ZGTNmqHjx4urbt6/Nx09FMgIAAADcZ3x9fXXx4sV07al3xPLz88twv3Pnzunjjz/Wa6+9lmYqV0JCgpKSkhQRESFvb2+VKFEiW3GQjAAAAAD2yIO39q1Zs6b279+vmJiYNIvYDx8+bN2ekcjISKWkpOg///mP/vOf/6TbHhQUpNDQUL3++uvZioNkBAAAALjPBAcHa/HixVqzZo31OSOJiYlav3696tSpo4oVK0r6cyF7bGysKlWqpEKFCumhhx7SnDlz0o03Y8YM3bx5U6+//roqVKiQ7ThIRgAAAID7TGBgoIKDgzVz5kxdv35dVapU0caNGxUREaHFixdb+02fPl0bNmzQrl27VKFCBZUqVUqtW7dON96yZcuUlJSU4baskIwAAAAAdrD3mR9mmTx5smbOnKlNmzYpJiZGDz30kObOnasmTZo4LQaLYRh59O1znDZu3c0OAUA+MPJM1g+Iyq53q9dyyDgA8q6CNR60e4ykX087IBLXsTNlrdkhZKruq++actxjk0eaclxHojICAAAA2OO+/2rfdi750MN9+/Zp2bJl1pJRRg4dOqSxY8c6OTIAAAAAjuJSlZHExEQNHDhQ33//vVJnj3l7e2v06NHq1atXmr7nz5/Xxo0bNWHCBDNCBQAAACTl3TUjrsClKiOLFi3SwYMHNXz4cG3atEmLFi1SQECA3nrrLb3++utKSUkxO0QAAAAADuJSlZGtW7eqa9euGjZsmCTJ399fzZo107x58zRz5kxduXJFM2bMkLu7u8mRAgAAALCXS1VGIiIiVL9+/XTtQ4YM0bRp07R37171799fsbGxzg8OAAAAyIhh0isfcKlkpHjx4rp27VqG2zp06KB58+bpl19+UWhoqKKiopwcHQAAAABHcqlkpFatWvriiy8y3d6sWTMtXbpUUVFRevddc+7nDAAAAKRBZcRmLpWMtGnTRocOHdKhQ4cy7RMYGKgPP/xQvr6+zgsMAAAAgMO51AL2rl27Kjg4WIUKFcqyX/Xq1bVlyxbduHHDOYEBAAAAcDiXSkYsFou8vLyy1bdIkSIqUqRILkcEAAAAZM1idgB5mEtN05KkU6dOadSoUerSpYv69++vdevWWR+A+FebNm1SrVq1TIgQAAAAgCO4VDJy7tw59ejRQzt37pSbm5vOnj2r8ePHq0+fPoqOjjY7PAAAACA9FrDbzKWSkRkzZqhIkSLavHmz1q9fr6+++kqTJk3SqVOn1LNnT509e9bsEAEAAAA4iEslI4cPH1bfvn1VuXJla1vnzp21Zs0aubm5qU+fPjpy5IiJEQIAAABpWQxzXvmBSyUjN27ckI+PT7r26tWra/Xq1Spbtqz69eunvXv3mhAdAAAAAEdyqbtplS9fXr/++muG23x8fLRy5UoNHjxYQ4cO1eOPP+7k6AAga2uiH3XQSDcdNA4c7U5X+z/jwhsOOCAS5HdJv542OwTAKVyqMtK4cWOFh4crKSkpw+3e3t5asmSJWrRood27dzs5OgAAACADLGC3mUslI127dlWDBg107NixTPu4u7trzpw5CgsL08MPP+zE6AAAAAA4kktN0woICNCsWbPu2c/NzU3jxo1zQkQAAADAPeSTKoUZXKoyAgAAAOD+QTICAAAAwBQuNU0LAAAAyGvyyzM/zEBlBAAAAIApqIwAAAAA9qAyYjMqIwAAAABMQTICAAAAwBRM0wIAAADswAJ221EZAQAAAGAKKiMAAACAPaiM2IzKCAAAAABTUBkBAAAA7MCaEdtRGQEAAABgCiojyPeuDn7MIeOUnv+NQ8ZB/nX5iUSzQ0AuK7zhgNkhSJKiNtV0yDh+T59wyDgAYKs8VRmJj4/Xjh07FB0dbXYoAAAAwJ8Mk175QJ5KRq5evaoRI0bo6NGjZocCAAAAwE4uNU3rzTffzHL7rVu3ZBiGVq1apT179shiseiNN95wTnAAAABARvJJlcIMLpWMrF69WhaLRYaR+SdqsVi0d+9e6/9PMgIAAADkTS6VjDRt2lSHDh3SoEGDNGDAALm7u6fZHhERodatW2vOnDkKCgoyKUoAAAAAjuBSa0aWLFmiSZMmad26dQoODta2bdvSbLdYLCZFBgAAAGTMYpjzyg9cKhmRpLZt22rbtm165plnNHbsWPXp00c///yz2WEBAAAAcDCXS0Ykyd3dXcOHD9fWrVvl4+Oj7t27a+zYsdzSFwAAAK6HW/vazCWTkVTlypXTrFmztHjxYh07dkxhYWFM1QIAAADyCZdawJ6ZJk2aaOPGjdqwYYMuX76satWqmR0SAAAAIEmyZHEnWGQtTyQjklSgQAGFhISYHQYAAAAAB3G5aVqnTp3SqFGj1KVLF/Xv31/r1q3L8LkjmzZtUq1atUyIEAAAAIAjuFQycu7cOfXo0UM7d+6Um5ubzp49q/Hjx6tPnz4sXgcAAIBrYgG7zVwqGZkxY4aKFCmizZs3a/369frqq680adIknTp1Sj179tTZs2fNDhEAAACAg7hUMnL48GH17dtXlStXtrZ17txZa9askZubm/r06aMjR46YGCEAAACQFg89tJ1LJSM3btyQj49Puvbq1atr9erVKlu2rPr166e9e/eaEB0AAAAAR3Kpu2mVL19ev/76a4bbfHx8tHLlSg0ePFhDhw7V448/7uTokFeVnv+N2SHgPpGSEG92CLhP/PTwGoeM006BDhkHAGzlUpWRxo0bKzw8XElJSRlu9/b21pIlS9SiRQvt3r3bydEBAAAAGWABu81cKhnp2rWrGjRooGPHjmXax93dXXPmzFFYWJgefvhhJ0YHAAAAwJFcappWQECAZs2adc9+bm5uGjdunBMiAgAAALKWXxaTm8GlKiMAAAAA7h8uVRkBAAAA8hwqIzajMgIAAADAFCQjAAAAAEzBNC0AAADADixgtx2VEQAAAACmoDICAAAA2IPKiM2ojAAAAAAwBckIAAAAAFMwTQsAAACwAwvYbUdlBAAAAIApqIwAAAAA9jAojdiKyggAAAAAU1AZAQAH2X7xsEPGaVcu0CHjIP/iHAFcC2tGbJdnKiN37txRVFSUEhMTzQ4FAAAAgAO4VGXk6NGjunLlilq2bGlt+/zzz/X+++/rxIkTMgxDBQoUUMOGDTV69GjVq1fPxGgBAAAA2MOlKiOTJ0/W559/bv158+bNGj58uK5cuaI+ffropZde0jPPPKOTJ0+qb9++OnTokHnBAgAAANKfT2A345UPuFRl5OTJk2rbtq3153fffVcNGzbUkiVL5OHhYW0fPXq0evfurenTp2v58uVmhAoAAADATi5VGUlISFDhwoUlSbdv39bFixfVt2/fNImIJBUrVkw9evTQ0aNHzQgTAAAAsLKkmPPKD1wqGalatap++uknSVLhwoXl5eWl2NjYDPvGxsaqUKFCzgwPAAAAgAO5VDLSs2dPffrpp9q1a5csFovCwsI0e/bsdBWQb7/9VkuXLlWTJk1MihQAAACAvVxqzUivXr10+PBhDRs2TIGBgQoICFBSUpJ69OihChUqqHTp0oqKitKlS5fk4+OjV1991eyQAQAAcL/LJ4vJzeBSlRFJmjBhgqZPny5J+vDDD3Xjxg0ZhqELFy7o0KFDSkxMVFhYmDZu3KgKFSqYHC0AAAAAW7lUZSRVhw4d1KFDB8XFxenChQu6deuWPD095efnJz8/P7PDAwAAAKx4ArvtXDIZSeXt7a1atWqZHQYAAACAXOBy07ROnTqlUaNGqUuXLurfv7/WrVsnw0ifbm7atIlEBQAAAOYzDHNe+YBLJSPnzp1Tjx49tHPnTrm5uens2bMaP368+vTpo+joaLPDAwAAAOBALpWMzJgxQ0WKFNHmzZu1fv16ffXVV5o0aZJOnTqlnj176uzZs2aHCAAAAMBBXCoZOXz4sPr27avKlStb2zp37qw1a9bIzc1Nffr00ZEjR0yMEAAAAEjLYpjzyg9cKhm5ceOGfHx80rVXr15dq1evVtmyZdWvXz/t3bvXhOgAAAAAOJJL3U2rfPny+vXXXzPc5uPjo5UrV2rw4MEaOnSoHn/8cSdHBwBZa1cu0OwQAKfbfvGw3WPwbwd5Xj6pUpjBpSojjRs3Vnh4uJKSkjLc7u3trSVLlqhFixbavXu3k6MDAAAA4EgulYx07dpVDRo00LFjxzLt4+7urjlz5igsLEwPP/ywE6MDAAAA4EguNU0rICBAs2bNumc/Nzc3jRs3zgkRAQAAAFnLL4vJzeBSlREAAAAA9w+XqowAAAAAeU4+eRq6GaiMAAAAADAFlREAAADADqwZsR2VEQAAAACmIBkBAAAAYAqmaQEAAAD2YJqWzaiMAAAAADAFlREAAADADixgtx2VEQAAAACmIBkBAAAAYAqmaQEAAAD2SGGelq2ojAAAAAAwBZURAHCQ7RcPO2ScduUCHTIO4Aycr4C4ta8dqIwAAAAAMEWeSkYSExN1584ds8MAAAAA4AAul4ysWbNGPXv2VL9+/fT1119Lko4cOaLu3burfv36atiwoTp06KCtW7eaHCkAAADw53NGzHjlBy6VjGzbtk1vvPGGLl68qKtXr2ro0KHat2+f+vfvr5s3b6pPnz7q1auXbt26pVGjRmn37t1mhwwAAADARi61gH3ZsmUKDAzUihUr5O7urilTpujll19WjRo1tGzZMhUqVEiSNGrUKHXv3l0LFixQq1atTI4aAAAA9zUjn5QpTOBSlZHffvtNnTp1kru7uySpR48eio2NVa9evayJiCR5e3srJCREJ06cMCtUAAAAAHZyqcpISkqKChb8X0gFChSQJGty8lfu7u5p+gIAAABmyC/rN8zgUpWRatWq6YsvvrD+vGvXLknS559/nqafYRjatm2bKlWq5NT4AAAAgPwiMTFRU6dOVYsWLVSvXj2FhIRo796999zv22+/1dixY9WuXTsFBgYqKChI48aNU1RUVI5jcKnSwnPPPaeRI0eqe/fuKl26tPbu3atHH31UxYoV08CBA9W6dWslJydry5Yt+umnn/Tmm2+aHTIAAACQJ40ZM0bbt2/Xs88+qypVqmjDhg0aPHiwli5dqsaNG2e635QpUxQTE6Pg4GBVqVJFFy5c0MqVK/Xll19qw4YN8vPzy3YMLpWMtG/fXleuXNHKlSt18eJFtWnTRq+//ro8PT310ksvWZMPNzc3de/eXT169DA3YAAAACAPTtM6cuSItmzZolGjRmnQoEGSpC5duqhjx46aPHmy1q1bl+m+Y8eOVaNGjeTm9r9JVi1atFDfvn21YsUKjRo1KttxuFQyIklhYWEKCwtL175w4UJduHBBV69eVeXKlVWyZEkTogMAAADyvvDwcLm5ualnz57WNg8PD4WEhGj69OmKiIhQhQoVMtz3kUceybCtRIkSOn36dI7icLlkJCsVK1ZUxYoVzQ4DAAAAsLLkwVv7Hj9+XJUqVVLx4sXTtNerV8+6PbNkJCO3bt3SrVu3clwwcLlk5NSpU5o3b57OnDmjkiVL6qmnnlK3bt1ksVjS9Nu0aZP++c9/6vjx4yZFCgAAAJgnKCgoy+2pN4PKSHR0tHx9fdO1p7bldDH6smXLdPfuXT311FM52s+l7qZ17tw59ejRQzt37pSbm5vOnj2r8ePHq0+fPoqOjjY7PAAAACBfiI+Pz/DxGR4eHtbt2fX9999rzpw5Cg4OVrNmzXIUh0tVRmbMmKEiRYroww8/VOXKlSVJn376qf7973+rZ8+eWrhwoapVq2ZylAAAAMBfpJhz2KwqH/fi6empxMTEdO0JCQnW7dlx5swZDR8+XA899JD++9//5jgOl6qMHD58WH379rUmIpLUuXNnrVmzRm5uburTp4+OHDliYoQAAABA3ufr65vhzKPUtuzcnvfSpUsaMGCAvL299cEHH8jb2zvHcbhUMnLjxg35+Pika69evbpWr16tsmXLql+/ftl6GAsAAADgDBbDMOVlj5o1a+r8+fOKiYlJ03748GHr9qxcv35d//jHP5SYmKhFixbl6Nkif+VSyUj58uX166+/ZrjNx8dHK1euVO3atTV06FCFh4c7OToAAAAgfwgODlZKSorWrFljbUtMTNT69etVp04d6x1so6KidObMGd29e9fa7/bt2xo0aJAiIyP1wQcfqEqVKjbH4VJrRho3bqzw8HD985//VMGC6UPz9vbWkiVLNGLECO3evTvdHbYAAAAAp8t7d/ZVYGCggoODNXPmTF2/fl1VqlTRxo0bFRERocWLF1v7TZ8+XRs2bNCuXbust/odPXq0jhw5om7duunMmTM6c+aMtX+RIkXUunXrbMfhUslI165ddeXKFR07dkz169fPsI+7u7vmzJmjCRMm6MSJE84NEAAAAMgnJk+erJkzZ2rTpk2KiYnRQw89pLlz56pJkyZZ7pf6N/gnn3yiTz75JM228uXL5ygZsRhGHnxKi4O1cetudggA8oHtFw87ZJx25QIdMg4A5Cc7U9aaHUKmglpOMOW4u74Ya8pxHcmlKiMAAABAnsN3+zZzqQXsAAAAAO4fVEYAAAAAO1gojNiMyggAAAAAU5CMAAAAADAF07QAAAAAe7CA3WZURgAAAACYgsoIAAAAYAdLitkR5F1URgAAAACYgsoIAAAAYA/WjNiMyggAAAAAU5CMAAAAADAF07QAAAAAezBLy2YkIwDgIO3KBZodAgA7bL942CHjcC0Ass/lk5H4+HjFx8fL09NTnp6eZocDAAAApGFhAbvNXC4ZSUxM1CeffKJt27bp+PHjiouLs27z9vZWzZo11b59e4WEhMjd3d3ESAEAAADYw6WSkatXr6p///46efKkqlSpopYtW8rX11ceHh5KSEhQdHS0jhw5orffflurVq3S0qVLVbp0abPDBgAAAGADl0pGJkyYoMjISC1ZskRNmzbNtN+3336rl19+WRMnTtSUKVOcGCEAAADwN0zTsplL3dp37969GjBgQJaJiCQ1bdpUAwYM0J49e5wUGQAAAABHc6nKyN27d1WkSJFs9S1cuLDu3r2byxEBAAAA95BidgB5l0tVRho2bKhly5bp8uXLWfa7dOmSli9frkaNGjkpMgAAAACO5lKVkbFjxyo0NFTt2rXTE088obp168rX11fu7u5KTExUdHS0jh07pq+++kpeXl4aM2aM2SEDAADgPsetfW3nUslI9erV9emnn2ru3LnauXOnduzYka5PqVKl1LVrVw0ZMkRly5Y1IUoAAAAAjuBSyYgklSlTRm+++abefPNNRUZGKjo62vrQQ19fX5UpU8bsEAEAAAA4gMslI39VpkyZNMnHuXPndPToUT344IMqXLiwiZEBAAAA/x/TtGzmcsnImjVrtHjxYsXGxqpZs2Z6/fXXlZCQoBdeeEFHjx6VJHl6eurll19Wv379TI4WAAAAgK1cKhn58ssv9cYbb6hmzZqqWrWqtm7dqrt37yo5OVne3t566623FB8frw0bNmjixImqXLmynnzySbPDBgAAwP2MyojNXCoZWbRokR555BEtX75cFotFixcv1tSpU9W8eXMtXrzY2q9Xr17q1KmTVqxYQTICAAAA5FEu9ZyR06dPq23btrJYLJKk1q1bKyUlRU899VSafu7u7nr66af1888/mxEmAAAAAAdwqcrI7du30yxML1q0qCTJz88vXV8/Pz/FxcU5LTYAAAAgQzyB3WYulYyULl1aUVFR1p89PDzUqVOnDJOR6OholShRwonRAQCA/KxduUCHjLP94mG7x3BULICrc6lkpE6dOjpy5Ij1Zy8vL02ZMiXDvj/99JOqV6/urNAAAACADPEEdtu5VDIydOhQXbhw4Z79rl27psTERHXp0iX3gwIAAACQK1wqGaldu7Zq1659z36lSpXSsmXLnBARAAAAcA9URmzmUnfTAgAAAHD/IBkBAAAAYAqXmqYFAAAA5DlM07IZlREAAAAApqAyAgAAANiDyojNqIwAAAAAMAXJCAAAAABTME0LAAAAsEeK2QHkXVRGAAAAAJiCyggAAABgBwsL2G1GZQQAAACAKaiMAAAAAPagMmIzKiMAAAAATEFlBAAc5LM/fnDIOB3LN3LIOADM0a5coN1jWAoUsHsMIznZ7jGA3EYyAgAAANgjhWlatnLJaVr79u3TsmXLtGnTJsXExGTY59ChQxo7dqyTIwMAAADgKC5VGUlMTNTAgQP1/fffy/j/C4G8vb01evRo9erVK03f8+fPa+PGjZowYYIZoQIAAAB/YgG7zVyqMrJo0SIdPHhQw4cP16ZNm7Ro0SIFBATorbfe0uuvv66UFB5vCQAAAOQXLlUZ2bp1q7p27aphw4ZJkvz9/dWsWTPNmzdPM2fO1JUrVzRjxgy5u7ubHCkAAAAAe7lUZSQiIkL169dP1z5kyBBNmzZNe/fuVf/+/RUbG+v84AAAAICMGIY5r3zApZKR4sWL69q1axlu69Chg+bNm6dffvlFoaGhioqKcnJ0AAAAABzJpZKRWrVq6Ysvvsh0e7NmzbR06VJFRUXp3XffdWJkAAAAQCaojNjMpZKRNm3a6NChQzp06FCmfQIDA/Xhhx/K19fXeYEBAAAAcDiXWsDetWtXBQcHq1ChQln2q169urZs2aIbN244JzAAAAAADudSyYjFYpGXl1em28+dO6fY2Fg9+OCDKlKkiIoUKeLE6AAAAIAM8AR2m7lUMiJJa9as0eLFixUbG6tmzZrp9ddfV0JCgl544QUdPXpUkuTp6amXX35Z/fr1MzlaAAAAALZyqWTkyy+/1BtvvKGaNWuqatWq2rp1q+7evavk5GR5e3vrrbfeUnx8vDZs2KCJEyeqcuXKevLJJ80OGwAAAPczgwdz28qlkpFFixbpkUce0fLly2WxWLR48WJNnTpVzZs31+LFi639evXqpU6dOmnFihUkIwAAAEAe5VJ30zp9+rTatm0ri8UiSWrdurVSUlL01FNPpenn7u6up59+Wj///LMZYQIAAAD/w619beZSycjt27dVuHBh689FixaVJPn5+aXr6+fnp7i4OKfFBgAAAMCxXGqaVunSpdM8Wd3Dw0OdOnXKMBmJjo5WiRIlnBgdAGStkMWlLqkA8jAjOdnsEACncKn/ctapU0dHjhyx/uzl5aUpU6Zk2Penn35S9erVnRUaAAAAkDFu7Wszl0pGhg4dqgsXLtyz37Vr15SYmKguXbrkflAAAAAAcoVLJSO1a9dW7dq179mvVKlSWrZsmRMiAgAAAO4hnywmN4NLLWAHAAAAcP8gGQEAAABgCpeapgUAAADkOUzTshmVEQAAAACmoDICAAAA2IPKiM2ojAAAAAAwBZURAAAAwB4pKWZHkGdRGQEAAABgCpIRAAAAAKZgmhYAAABgDxaw24zKCAAAAABTUBkBAAAA7EFlxGZURgAAAACYgmQEAAAAgCnyVDISHx+vHTt2KDo62uxQAAAAgD+lGOa88oE8lYxcvXpVI0aM0NGjR80OBQAAAICdXGoB+5tvvpnl9lu3bskwDK1atUp79uyRxWLRG2+84ZzgAAAAgAwYBk9gt5VLJSOrV6+WxWKRkcUdCSwWi/bu3Wv9/0lGAAAAgLzJpZKRpk2b6tChQxo0aJAGDBggd3f3NNsjIiLUunVrzZkzR0FBQSZFCQAAAPxFPlm/YQaXWjOyZMkSTZo0SevWrVNwcLC2bduWZrvFYjEpMgAAAACO5lLJiCS1bdtW27Zt0zPPPKOxY8eqT58++vnnn80OCwAAAICDuVwyIknu7u4aPny4tm7dKh8fH3Xv3l1jx47llr4AAABwPYZhzisfcMlkJFW5cuU0a9YsLV68WMeOHVPfvn2ZqgUAAADkEy61gD0zTZo00caNG7VhwwZdvnxZ1apVMzskAAAA4E8p3NrXVnkiGZGkAgUK6OGHH1ZsbKzKli1rdjgAAAAA7ORyyciaNWu0ePFixcbGqlmzZnr99deVkJCgoUOH6tixY5IkT09Pvfzyy+rXr5/J0QIAAACwlUslI19++aXeeOMN1axZU1WrVtXWrVt19+5dJScnq2jRonrrrbd0584dbdy4URMnTlTlypX15JNPmh02AAAA7mf5ZDG5GVwqGVm0aJEeeeQRLV++XBaLRYsXL9bUqVPVvHlzLV682Nqvd+/e6tSpk1asWEEyAgAAAORRLnU3rdOnT6tt27bWO2a1bt1aKSkpeuqpp9L0c3d319NPP83zRwAAAGA6IyXFlFd+4FLJyO3bt1W4cGHrz0WLFpUk+fn5pevr5+enuLg4p8UGAAAAwLFcappW6dKlFRUVZf3Zw8NDnTp1yjAZiY6OVokSJZwYXe67Ovgxu8coPf8bB0QCwBZNDoU4ZJziOuWQcQAATsKaEZu5VDJSp04dHTlyxPqzl5eXpkyZkmHfn376SdWrV3dWaAAAAAAczKWSkaFDh+rChQv37Hft2jUlJiaqS5cuuR8UAAAAgFzhUslI7dq1Vbt27Xv2K1WqlJYtW+aEiAAAAIB7SGGalq1cagE7AAAAgPuHS1VGAAAAgDzHyB+32TUDlREAAAAApiAZAQAAAGAKpmkBAAAAdjBYwG4zKiMAAAAATEFlBAAAALAHC9htRmUEAAAAuA8lJiZq6tSpatGiherVq6eQkBDt3bs3W/vevHlTr7/+upo0aaL69esrLCxMR48ezXEMJCMAAACAHYwUw5SXvcaMGaMlS5aoY8eOGjdunAoWLKjBgwfru+++y3K/lJQUDRo0SJs3b1ZoaKheeeUVXb9+Xc8++6zOnDmToxhIRgAAAID7zJEjR7RlyxaNGDFC//znP9WzZ08tW7ZM5cuX1+TJk7PcNzw8XD/99JP++9//6sUXX1RoaKiWL1+uggULatasWTmKg2QEAAAAuM+Eh4fLzc1NPXv2tLZ5eHgoJCRER48eVURERKb7bt++XSVLllRwcLC1rVSpUmrfvr2++OILxcfHZzsOkhEAAADAHkaKOS87HD9+XJUqVVLx4sXTtNerV8+6Pat9a9euLTe3tKlEQECAEhISdPbs2WzHwd20AAAAgDwoKCgoy+27du3KdFt0dLR8fX3Ttae2RUVFZblvgwYN0rX7+flZ961du3aWsaUiGZG0M2Wt2SE4ztyRZkcAwF7cIRIA8hSz/pa8VzKSlfj4eLm7u6dr9/DwsG7P6b6pbTmZpkUyAgAAAORBWVU+7sXT01OJiYnp2hMSEqzbc7pvaltW+/4da0YAAACA+4yvr6+io6PTtae2pU65ysm+qVO7str370hGAAAAgPtMzZo1df78ecXExKRpP3z4sHV7Vvv+8ssvSklJO6/4yJEj8vDwULVq1bIdB8kIAAAAcJ8JDg5WSkqK1qxZY21LTEzU+vXrVadOHVWsWFHSn9WOM2fO6O7du2n2vX79usLDw61t165dU3h4uJ588skcTdNizQgAAABwnwkMDFRwcLBmzpyp69evq0qVKtq4caMiIiK0ePFia7/p06drw4YN2rVrlypUqCBJateunerXr69x48bp7NmzKlmypFatWqWkpCSNGDEiR3GQjAAAAAD3ocmTJ2vmzJnatGmTYmJi9NBDD2nu3Llq0qRJlvsVKFBAH3zwgaZMmaIVK1YoPj5eAQEBeuedd1S9evUcxWAxDMOw55cAAAAAAFuwZgQAAACAKUhGAAAAAJiCZAQAAACAKUhGAAAAAJiCZAQAAACAKUhGAAAAAJiCZAQAAACAKXjoYSYSExM1a9Ysffrpp4qJiZG/v79GjBihFi1aODWOI0eOaOPGjTpw4ID++OMPlShRQoGBgXr55ZdVtWpVp8byd5s2bdIrr7wid3d3HT161OnH/+WXXzR79mz9+OOPio+PV/ny5dW1a1c9//zzTovh3LlzmjVrln744QfduHFDZcuWVdu2bfX888+rWLFiuXLMW7duadGiRTp69KiOHj2q69eva9SoURo0aFC6vmfOnNGECRP0ww8/qFChQmrRooXGjh0rHx8fp8SRkpKijRs3aseOHTp+/LhiYmJUoUIFdejQQQMGDJCHh4fdcWQ3loz0799f33zzjXr27Km3337bqXEYhqE1a9Zo9erV+u233+Tp6Sl/f3+98sorqlevnlNj2bZtm5YsWaKzZ8/Kzc1N1apV07PPPqsOHTrYFUNOrl+5ea5mNxZnnK+2XtMdfa7mNJbcPF9zEkdunaupfv75Z82dO1e//PKLrly5Ii8vLz344IMaMGCAWrZsmaZvbp6z2YnDWdfXnLwnf5Ub5yzyJ5KRTIwZM0bbt2/Xs88+qypVqmjDhg0aPHiwli5dqsaNGzstjoULF+rHH39UcHCwatSooejoaH344Yd65plntHr1atWoUcNpsfzVrVu3NGXKFHl5eSkpKcnpx//66681ZMgQ1a5dW0OHDpWXl5cuXLigy5cvOy2GS5cuqXv37ipSpIh69+6tUqVK6dixY1q0aJG+++47rVmzJleOe/36dc2ZM0dly5ZV7dq1tW/fvgz7Xb58WaGhofL29tbIkSN1584dLVq0SCdPntS6devs/g9VduK4c+eOxo4dq/r166tXr14qXbq0fvrpJ82ePVvffvutli9fLovFYlcc2Y3l73bs2KFDhw7ZfWxb43jttde0adMmPf300woNDdXt27d14sQJRUdHOzWWFStW6D//+Y9atGih//u//1NSUpI2b96skSNHKiYmRr1797Y5huxev3L7XM1uLM44X225pufGuZrTWHLzfM1uHLl5rqa6cOGCEhMT9cwzz6hMmTK6ffu2duzYoSFDhujNN9+0HiO3z9nsxOGs62t235O/yq1zFvmUgXQOHz5s+Pv7G/Pnz7e2xcfHG61btza6devm1Fh++OEHIyEhIU3bb7/9ZtStW9cYOXKkU2P5qylTphjt2rUzRo0aZdStW9epx46NjTUee+wxY9iwYUZycrJTj/1Xc+fONfz9/Y0TJ06kaX/nnXcMf39/4/Tp07ly3ISEBOPy5cuGYRjGhQsX0p2rqd544w2jbt26RkREhLVt3759hr+/v7Fy5UqnxJGQkGD88MMP6fadPXu24e/vb+zZs8fuOLIby1/Fx8cbLVu2NN577z3D39/f+Ne//uXUOLZs2WL4+/sbO3bscMhx7Ymlbdu2xjPPPGOkpKRY2+Lj441mzZoZISEhdsWQ3etXbp+r2Y3FGedrTq/puXWu5iSW3D5fsxtHbp6rWUlKSjKefvppo02bNtY2Z5yz94rDWdfX7MTyV7l5ziJ/Ys1IBsLDw+Xm5qaePXta2zw8PBQSEqKjR48qIiLCabE0bNhQ7u7uadqqVKmihx56SKdPn3ZaHH917tw5LV26VGPHjlXBgs4vrm3evFlXrlzRyJEj5ebmplu3biklJcXpccTGxkqSfH1907Sn/uzp6Zkrx3V3d1eZMmXu2W/Hjh164oknVL58eWvbY489pipVqig8PNwpcbi7u6thw4bp2tu0aSPpz2kOjpDd9yTVggULZBiGBgwY4JDj5zSOpUuXql69emrTpo1SUlJ069Yth8aRk1hiY2Pl4+OT5htUDw8PFS9e3O5zOLvXr9w+V7MbizPO15xe03PrXM1JLLl9vmY3jtw8V7NSoEABlS1bVjdv3rS2OeOcvVcczrq+ZieWv8rNcxb5E8lIBo4fP65KlSqpePHiadpT58UeP37cjLCsDMPQlStXVLJkSVOO/8477+jRRx/VE088Ycrxv/32W3l7eysyMlLt2rVTw4YN1bBhQ40fP1537txxWhyp0/Vee+01/fzzz7p8+bJ27typRYsWqVOnTmn+I+VskZGRunr1qurWrZtuW7169fTLL7+YENX/XLlyRZJUokQJpx/74sWLWrBggUaPHp2rf8BkJi4uTkeOHFFAQICmT5+uRo0aqWHDhmrVqpU2bdrk9HgeeeQR7dmzR0uXLtWFCxd07tw5TZkyRb///rsGDhzo8OP9/fpl5rma3Wtpbp+vmcVhxrn691jMOl8zek+cea7eunVL165d0++//67Fixdr7969atasmSTnnrNZxZGZ3DpfsxOL2ddX5E2sGclAdHR0um+7pf994x0VFeXskNLYtGmTIiMjNXz4cKcf+8svv9S+ffv06aefOv3Yqc6dO6fk5GS98MILCgkJ0ahRo/TDDz9o2bJlunbtmt5//32nxPHEE0/oxRdf1IIFC/TFF19Y2/v06aN//etfTokhM6nnaGbncVxcnG7fvi0vLy9nhybpzzniRYoUMSWhnThxomrVqqWnnnrK6ceWpPPnz8swDG3ZskUFCxbUK6+8omLFimnlypV65ZVXVLhwYes3m87wr3/9S9evX9eECRM0YcIESZK3t7fmzp2bKzfs+Pv1y8xzNbvX0tw+XzOLw4xz9e+xmHW+ZvSeOPNcfeONN7R582ZJkpubm9q0aaPXX39dknPP2aziyExuna/ZicXs6yvyJpKRDMTHx6crGUuyLkiLj493dkhWZ86c0dtvv6369eurW7duTj12YmKiJkyYoF69eunBBx906rH/6vbt27pz54569eql8ePHS5Latm0r6c/pBCdOnFDNmjWdEkvFihXVoEEDtW3bVn5+fjpw4IA+/PBDFS5cWK+++qpTYshIQkKCJN3zPDYjGZk3b56++eYbvf76606v7u3fv187duzQxx9/7NTj/tXt27clSTdu3NDHH3+swMBASVLr1q3Vpk0bzZkzx6nJSOHChVW9enX5+voqKChIiYmJWr16tUaMGKElS5ZY43OEjK5fZp2r2b2W5vb5mlkcZpyrGcVixvma2XvizHN18ODBeuaZZxQVFaXPPvtMycnJSkxMlOTcczarODKSm+frvWJxhesr8iamaWXA09Mzw3/sqRcgs0qP0dHRGjx4sIoWLapZs2apQIECTj3+0qVLdf36db344otOPe7fpb7/HTt2TNPeqVMnSdIPP/zglDi2bNmi8ePH69///rf69Omj1q1ba9y4cRo8eLAWL16sX3/91SlxZCT1P4iudh5v3bpVM2bMUEhIiEJDQ5167KSkJP33v/9V586dHXLrXFulfjYVKlRI88eTp6en2rZtqxMnTuTKGpLMjBgxQufPn9e0adPUoUMHdenSRcuXL5ePj49Db8eZ2fXLjHM1u9fS3D5fM4vDjHP1Xp+Ps87XrD4bZ52rkvTQQw/pscceU5cuXbRgwQLdvn1bQ4cOlWEYTj1ns4rj73L7fM0qFle5viJvIhnJgK+vb4a3K0xt8/Pzc3ZIio2N1fPPP6/Y2FgtXLgwR4t1HXX8uXPnqnv37oqLi1NERIQiIiJ0+/ZtGYahiIgIXb161SmxpL7/pUuXTtOeem/3jBbU5YaPPvpINWvWVMWKFdO0t27dWoZh6Mcff3RKHBlJfY8yO4+9vb2dXhXZt2+fXn31VT355JN66623nHpsSdq4caN+++039ezZ03r+pt6M4tatW4qIiHDKmqPUzyajZxGULl1ahmEoLi4u1+OQ/rxl5969exUUFJSm3d3dXY8//rh+/vlnh1SCs7p+Oftcze61NLfP16zicPa5mp3Pxxnna1ZxOOtczYjFYlFwcLCOHj2q3377zbTr69/j+CtnX1//HourXF+RNzFNKwM1a9bU/v37FRMTk2YR++HDh63bnSkhIUFDhgzRuXPntGTJElOmSMXExOj27dtauHChFi5cmG57UFCQnnzySc2fPz/XY6lTp4727dunyMhIVatWzdqe+oyRUqVK5XoM0p+LBIsUKZKuPTk5Oc3/mqFMmTLW55783ZEjR1SrVi2nxnP48GENHz5cdevW1YwZM0y5C9ulS5d09+7dDO+J/9lnn+mzzz7TzJkzFRwcnKtxlClTRr6+voqMjEy37fLlyypQoEC6m2fkltSFrhmdq0lJSTIMw+7z+F7XL2eeq9m9lub2+XqvOJx5rmbn83HG+XqvOJxxrmYlNdGJi4tTtWrVTLu+/jWOVGZdX/8ai6tcX5E3kYxkIDg4WIsXL9aaNWusTytOTEzU+vXrVadOnXTfhOem5ORkvfzyyzp06JDef/99NWjQwGnH/qvSpUtrzpw56dqXL1+uH3/8UTNmzHDYk5LvpX379vrggw+0bt06NW3a1Nr+8ccfy83NLU1bbqpatar27t2rU6dO6aGHHrK2p95hpk6dOk6JIzNt27bV+vXr9ccff1jv7PXtt9/q3LlzCgsLc1ocZ86c0aBBg1S+fHnNnz/ftGmOHTp0yPCPhGHDhql58+bq3bu3AgICnBJL+/bttXz5cu3bt896N5qbN29q+/btatiwodPeo8qVK8vNzU1btmxRaGio3Nz+LJbHxcVp9+7dqlKlSoYJd3Zl9/rljHM1u7Hk9vmanTicda5m9z3J7fM1O3Hk9rma6urVq+mq7omJidq4caM8PT1VvXp1Sbl/zmY3DmdcX7MTS5EiRVzm+oq8h2QkA4GBgQoODtbMmTN1/fp1ValSRRs3blRERIQWL17s1FgmTpyo3bt3q2XLlrpx40a6u1h17tzZKXEULlxYrVu3Ttf++eef66effspwW26pXbu2unXrpk8++URJSUl69NFH9cMPP+izzz5TWFiYKlWq5JQ4Bg4cqL1796pv377q27evfHx8tH//foWHh6t58+a5mjiuXLlSN2/etD7r5MCBA0pKSpIkhYWFqWjRohoyZIjCw8PVr18/Pfvss4qPj9eiRYv04IMPqnv37k6Jw2KxaMCAAbp586YGDBigL7/8Ms3+lSpVctj7dK9Yqlevbv0P+N+VL1/eYedwdj6bwYMHa9u2bXrxxRfVv39/FS1aVGvXrtWtW7c0evRoh8SRnVhKlSql7t27a82aNQoNDVX79u119+5drV27VpGRkZo2bZpdx8/u9csZ52p2YomLi8v18zU7cTjrXM3u55Pb52t24sjtczXVyJEj5e7urgYNGsjPz0+RkZHavHmzzp07pzFjxlgTntw+Z7MThzPO1+zG4qxzFvmTxchoFRSUkJCgmTNnatOmTYqJidFDDz2kESNGOP1WpGFhYfruu+8y3W7mImlJGjNmjLZs2aKjR4869bh3797V/PnztX79ekVFRals2bLq0aOHBg4caP3GzBmOHTum9957T7/88ouuXbsmPz8/dejQQcOHD8/Vb7dbtWqlP/74I8Ntu3btUoUKFSRJp06d0sSJE/Xjjz+qYMGCevzxxzVmzJgMb0mZG3FISjfH+6+6du2qiRMnOiWW1Pfk72rUqKGePXs6bAFsduO4cOGCJk2apP379+vu3bsKCAjQyJEj1ahRI4fEkd1YkpOT9fHHH2vt2rX6/ffflZycrJo1a2rgwIF2/wGRk+tXbp+r2YklIiIi189Xe67pjj5XcxJLbp6v2Y0jN8/VVJ988ok2btyoM2fOKCYmRt7e3qpTp45CQ0PTnRu5ec5mJw5nnK/ZjSUzjj5nkT+RjAAAAAAwBXfTAgAAAGAKkhEAAAAApiAZAQAAAGAKkhEAAAAApiAZAQAAAGAKkhEAAAAApiAZAQAAAGAKkhEAAAAApiAZAYA8avbs2apRo4YiIiKybHMlERERqlGjhmbPnm12KAAAF1DQ7AAAIC85cOCAnn322TRthQsXVsWKFdW+fXsNGDBAHh4eJkVnn4iICG3YsEGtW7dWrVq1zA4HAHAfIBkBABu0a9dOQUFBkqSrV69qy5Ytmjlzpn788UctXLjQtLiGDh2qQYMGyd3dPcf7/vHHH3rvvfdUvnx5khEAgFOQjACADWrWrKnOnTtbfw4LC1NISIj27t2rI0eOqF69eun2iY+PV8GCBVWwYO5denN7fAAAHIk1IwDgAIUKFdJjjz0mSTp//rzCwsLUqlUr/fHHHxo5cqQeffRRBQYG6vLly5KkuLg4vfvuu2rXrp3q1q2rxo0b64UXXtCJEyfSjR0XF6f//Oc/at68uerVq6euXbtq27ZtGcaR2ZqRW7duafbs2erYsaPq1aunRx55RN26ddPKlSut+6VOPxs7dqxq1KihGjVqKCwsLM0427dvV9++fdWwYUPVq1dPXbp00dq1azOM5bPPPtPTTz+tgIAAtWjRQhMmTFB8fHwO3lUAQH7H12cA4CC//fabJKlUqVKS/kwAQkNDFRAQoJdeekm3bt2Sl5eX4uLi1Lt3b50/f15dunRRzZo1dfPmTX388cfq1auXPvzwQ9WpU0eSlJSUpOeff14//vij2rRpo6ZNm+rixYt67bXXVLVq1WzFFRsbqz59+ujkyZNq2bKlunXrpoIFC+rkyZPasWOH+vbtqzZt2igpKUnz5s1Tz5491ahRI0mSj4+PdZxZs2Zpzpw5evTRRzV8+HB5eHjo66+/1vjx4/X7779r9OjR1r6rVq3Sm2++qSpVqmjYsGEqVKiQNm/erO+//94h7zUAIH8gGQEAG8THx+vatWuSpGvXrmnjxo364osvVKFCBT388MOSpBs3bqh79+5p/kiXpHfeeUe//fabPvzwQwUGBlrbe/furU6dOmnixIlasWKFJGnjxo368ccf9eyzz2rcuHHWvq1bt1bv3r2zFeu7776rkydPasyYMerfv3+abSkpKZL+nHYWExOjefPmqX79+mmmoEnSL7/8ovfff19hYWEaP368tT00NFT//vf/a+9+Qpr+4ziOvzYUN8vZFoOKvjHJLqGgYNNRhwg6bQqKYdBBEIT0NMGDZ3+wg4cUuiRLwUrpUAT2BwkFMUkqwpMgOhH0oAd1jGGQyfY7/NiX1vIP/n745ZfPB+zy/Xy+38+bXcaLz+f93V8aGBhQU1OTDMNQMplUT0+PLly4oBcvXqioqMice/fu3UPVDAA4GTimBQBH0N/fr0AgoEAgoGAwqGg0qurqag0ODmY1j7e2tmbdl06nNTo6qoqKChmGoa2tLfOzu7ur69ev6+vXr+Zxpvfv30uS7t+/n/WcyspKBQKBA+tMpVJ68+aNDMNQc3NzzrjdfrifgdevXyudTquxsTGr5q2tLd26dUupVEofP36UJE1PT+vbt2+6d++eGUQkyeFwqKWl5VDrAQBOBnZGAOAIGhoaVFtbK5vNpoKCAvl8PvN4VobH41FxcXHWtXg8rng8ri9fvuwbJuLxuM6fP6+VlRW53W6dPXs2Z05paakZAPZ7TiKRkN/vP3Tw+J2lpSVJytkx+dnGxoYkaXV11azvV1euXDlyDQCAPw9hBACOwDAMs2F9L06nM+da5ljUtWvX1N7evue9vwYbq2Xq7u/v3/O1wYZhHGdJAIA/AGEEAI6Rx+ORy+VSIpE4MMxI0qVLl7S8vKzNzc2c3ZFYLHbg/W63W8XFxZqfn1cqldp3d8Rms+055vP59OHDB3m9XrO5fi+ZUBKLxXTz5s2sscXFxQNrBgCcHPSMAMAxstvtqqur08LCgl69evXbOZnjTpJ0+/ZtSdKjR4+y5szOzmpmZuZQ64VCIa2urppN8T/L7HhIUmFhoSQpkUjkzMscz3rw4IF+/PiRM55MJrWzsyNJunHjhgoLCzU8PKxkMmnO+f79uwYHBw+sGQBwcrAzAgDHrKOjQ7Ozs+rq6tL4+LiqqqrkdDq1trammZkZFRQUmMGhvr5eL1++1JMnT7S+vq6amhqtra1peHhYV69e1dzc3IHrhcNhff78WZFIRJ8+fZLf71d+fr4WFxe1vLysoaEhSf/0eJw6dUojIyNyOBxyuVzyeDwKBAIqLy9XOBxWX1+fQqGQQqGQzp07p83NTS0sLGhiYkJv377VxYsXVVRUpM7OTnV3d6uxsVENDQ3Kz8/X6Ojov+pbAQD8eQgjAHDMTp8+rZGREQ0NDendu3eanp6W3W6X1+s1/0gwIy8vT48fP1Zvb6/GxsY0OTmpy5cvKxKJKBaLHSqMuFwuPX/+XNFoVGNjY5qampLT6ZTP51N9fb05z+FwqLe3V319fYpEItrZ2ZHf7zcb7dva2lRWVqanT5/q2bNn2t7eltvtVklJicLhsLxer/mszJu0otGoHj58qDNnzigYDOrOnTsKBoP/3ZcJAPhfs6XT6bTVRQAAAAA4edgvBwAAAGAJwggAAAAASxBGAAAAAFiCMAIAAADAEoQRAAAAAJYgjAAAAACwBGEEAAAAgCUIIwAAAAAsQRgBAAAAYAnCCAAAAABLEEYAAAAAWIIwAgAAAMAShBEAAAAAlvgb1xsLNMbRJykAAAAASUVORK5CYII=\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Baseline Random Forest evaluation complete\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'Model': 'Random Forest (Baseline)',\n",
              " 'Training Time': 9.24245810508728,\n",
              " 'Prediction Time': 0.1706218719482422,\n",
              " 'Accuracy': 0.9139460610361959,\n",
              " 'Precision': 0.8703360538278941,\n",
              " 'Recall': 0.9139460610361959,\n",
              " 'F1 Score': 0.8765503040021617}"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ],
      "source": [
        "\n",
        "# SECTION 5. BASELINE RANDOM FOREST\n",
        "\n",
        "\n",
        "rf = RandomForestClassifier(\n",
        "    n_estimators=100,\n",
        "    random_state=42,\n",
        "    n_jobs=-1\n",
        ")\n",
        "\n",
        "rf_results, y_pred_rf = evaluate_model(\n",
        "    \"Random Forest (Baseline)\",\n",
        "    rf,\n",
        "    X_train,\n",
        "    X_test,\n",
        "    y_train,\n",
        "    y_test\n",
        ")\n",
        "\n",
        "print(\"\\nBaseline Random Forest evaluation complete\")\n",
        "rf_results\n",
        "\n",
        "\n",
        "#A default Random Forest classifier is trained to establish baseline performance.\n",
        "#This allows us to see how well the model performs before tuning.\n",
        "#The evaluation function is used to measure performance and visualise results on the test dataset.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "1RKXvJGzPydX",
        "outputId": "c76dc428-3949-4caf-9a8f-af381a604eb1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Gradient Boosting  RESULTS\n",
            "Training Time: 22.134s\n",
            "Prediction Time: 0.067s\n",
            "Accuracy: 0.9065\n",
            "Precision: 0.8619\n",
            "Recall: 0.9065\n",
            "F1 Score: 0.8756\n",
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.00      0.00      0.00       228\n",
            "           1       1.00      0.96      0.98       227\n",
            "           2       0.00      0.00      0.00        17\n",
            "           3       0.00      0.00      0.00         2\n",
            "           4       1.00      0.18      0.31       411\n",
            "           5       0.00      0.00      0.00        41\n",
            "           6       1.00      1.00      1.00         2\n",
            "           7       0.95      0.97      0.96       479\n",
            "           8       1.00      1.00      1.00         2\n",
            "           9       0.00      0.00      0.00         4\n",
            "          10       0.00      0.00      0.00        94\n",
            "          11       0.00      0.00      0.00       310\n",
            "          12       0.02      0.11      0.03         9\n",
            "          13       0.00      0.00      0.00         2\n",
            "          14       0.98      1.00      0.99      6654\n",
            "          15       0.81      0.69      0.75       206\n",
            "          16       0.87      0.98      0.93     11245\n",
            "          17       0.00      0.00      0.00         1\n",
            "          18       1.00      1.00      1.00         1\n",
            "          19       0.87      0.97      0.92        35\n",
            "          20       0.94      0.96      0.95       371\n",
            "          21       0.00      0.00      0.00       211\n",
            "          22       0.00      0.00      0.00         9\n",
            "          23       0.00      0.00      0.00         4\n",
            "          24       0.00      0.00      0.00        93\n",
            "          25       0.86      0.99      0.92       698\n",
            "          26       0.00      0.00      0.00         8\n",
            "          27       0.98      1.00      0.99       540\n",
            "          28       0.00      0.00      0.00        43\n",
            "          29       0.00      0.00      0.00        99\n",
            "          31       0.89      1.00      0.94       104\n",
            "          32       0.99      0.84      0.91       107\n",
            "          33       0.27      0.01      0.02       279\n",
            "          34       0.00      0.00      0.00         4\n",
            "          35       0.00      0.00      0.00         1\n",
            "          36       0.00      0.00      0.00         3\n",
            "\n",
            "    accuracy                           0.91     22544\n",
            "   macro avg       0.40      0.38      0.38     22544\n",
            "weighted avg       0.86      0.91      0.88     22544\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            " Gradient Boosting evaluation complete\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'Model': 'Gradient Boosting ',\n",
              " 'Training Time': 22.134079456329346,\n",
              " 'Prediction Time': 0.06667971611022949,\n",
              " 'Accuracy': 0.9064939673527325,\n",
              " 'Precision': 0.861866767182059,\n",
              " 'Recall': 0.9064939673527325,\n",
              " 'F1 Score': 0.8755915052789309}"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ],
      "source": [
        "\n",
        "# SECTION 6. GRADIENT BOOSTING\n",
        "\n",
        "\n",
        "gb = GradientBoostingClassifier(\n",
        "    n_estimators=10,       # drastically reduced\n",
        "    learning_rate=0.3,     # faster convergence\n",
        "    max_depth=2,           # tiny trees\n",
        "    subsample=0.5,         # sample only 50% of data per tree\n",
        "    random_state=42\n",
        ")\n",
        "\n",
        "gb_results, y_pred_gb = evaluate_model(\n",
        "    \"Gradient Boosting \",\n",
        "    gb,\n",
        "    X_train,\n",
        "    X_test,\n",
        "    y_train,\n",
        "    y_test\n",
        ")\n",
        "\n",
        "print(\"\\n Gradient Boosting evaluation complete\")\n",
        "gb_results\n",
        "\n",
        "\n",
        "#A lightweight version of Gradient Boosting is trained as a baseline comparison.\n",
        "#Gradient Boosting takes longer to train, so smaller parameters were used to keep execution manageable.\n",
        "#The outputs help compare how GB behaves differently from Random Forest before tuning.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8Bq4bmbJR_ea",
        "outputId": "516ec2ae-7313-4327-8802-dbebcabda602"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            " HYPERPARAMETER TUNING  RANDOM FOREST\n",
            "\n",
            "Running GridSearchCV for Random Forest...\n",
            "Fitting 2 folds for each of 4 candidates, totalling 8 fits\n",
            "\n",
            "Best Parameters (Random Forest):\n",
            "{'max_depth': None, 'max_features': 'sqrt', 'n_estimators': 100}\n",
            "Best Weighted F1 Score (RF): 0.9980662680065071\n",
            "HYPERPARAMETER TUNING — GRADIENT BOOSTING\n",
            "\n",
            "Running GridSearchCV for Gradient Boosting...\n",
            "Fitting 2 folds for each of 2 candidates, totalling 4 fits\n",
            "\n",
            "Best Parameters (Gradient Boosting — MICRO):\n",
            "{'learning_rate': 0.1, 'max_depth': 2, 'n_estimators': 30}\n",
            "Best Weighted F1 Score (GB): 0.9907667846310075\n",
            "\n",
            "Hyperparameter tuning for BOTH models completed successfully\n"
          ]
        }
      ],
      "source": [
        "\n",
        "# SECTION 7. HYPERPARAMETER TUNING (RF + GB)\n",
        "\n",
        "\n",
        "\n",
        "print(\" HYPERPARAMETER TUNING  RANDOM FOREST\")\n",
        "\n",
        "\n",
        "\n",
        "# GRID SEARCH — RANDOM FOREST\n",
        "\n",
        "\n",
        "param_grid_rf = {\n",
        "    'n_estimators': [50, 100],\n",
        "    'max_depth': [10, None],\n",
        "    'max_features': ['sqrt']\n",
        "}\n",
        "\n",
        "grid_rf = GridSearchCV(\n",
        "    RandomForestClassifier(random_state=42, n_jobs=-1),\n",
        "    param_grid_rf,\n",
        "    cv=2,                        # Fast CV\n",
        "    scoring='f1_weighted',\n",
        "    verbose=1,\n",
        "    n_jobs=-1\n",
        ")\n",
        "\n",
        "print(\"\\nRunning GridSearchCV for Random Forest...\")\n",
        "grid_rf.fit(X_train, y_train)\n",
        "\n",
        "print(\"\\nBest Parameters (Random Forest):\")\n",
        "print(grid_rf.best_params_)\n",
        "\n",
        "print(\"Best Weighted F1 Score (RF):\", grid_rf.best_score_)\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "print(\"HYPERPARAMETER TUNING — GRADIENT BOOSTING\")\n",
        "\n",
        "\n",
        "\n",
        "#GRID SEARCH — GRADIENT BOOSTING\n",
        "\n",
        "param_grid_gb = {\n",
        "    'n_estimators': [30],      # one value\n",
        "    'learning_rate': [0.1, 0.2],  # two values\n",
        "    'max_depth': [2]           # one value\n",
        "}\n",
        "\n",
        "grid_gb = GridSearchCV(\n",
        "    GradientBoostingClassifier(random_state=42),\n",
        "    param_grid_gb,\n",
        "    cv=2,                      # fast\n",
        "    scoring='f1_weighted',\n",
        "    verbose=1,\n",
        "    n_jobs=-1\n",
        ")\n",
        "\n",
        "print(\"\\nRunning GridSearchCV for Gradient Boosting...\")\n",
        "grid_gb.fit(X_train, y_train)\n",
        "\n",
        "print(\"\\nBest Parameters (Gradient Boosting — MICRO):\")\n",
        "print(grid_gb.best_params_)\n",
        "\n",
        "print(\"Best Weighted F1 Score (GB):\", grid_gb.best_score_)\n",
        "\n",
        "print(\"\\nHyperparameter tuning for BOTH models completed successfully\")\n",
        "\n",
        "\n",
        "\n",
        "#GridSearchCV is used to identify the best hyperparameters for both models.\n",
        "#A reduced search space is used to make tuning computationally feasible while still improving performance.\n",
        "#This section fulfils the requirement to tune both ensemble models and compare their optimised performance.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 930
        },
        "id": "BgDVrqozSxJD",
        "outputId": "fb1a0e1b-0003-466b-ba37-a2b756349828"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Feature importance plots completed.\n"
          ]
        }
      ],
      "source": [
        "\n",
        "# SECTION 8. FEATURE IMPORTANCE (RF & GB)\n",
        "\n",
        "\n",
        "# Refit RF using best parameters (FAST GridSearch)\n",
        "best_rf = RandomForestClassifier(\n",
        "    n_estimators=grid_rf.best_params_['n_estimators'],\n",
        "    max_depth=grid_rf.best_params_['max_depth'],\n",
        "    max_features=grid_rf.best_params_['max_features'],\n",
        "    random_state=42,\n",
        "    n_jobs=-1\n",
        ")\n",
        "\n",
        "best_rf.fit(X_train, y_train)\n",
        "\n",
        "\n",
        "# Random Forest Feature Importance\n",
        "\n",
        "\n",
        "importances_rf = best_rf.feature_importances_\n",
        "indices_rf = np.argsort(importances_rf)[::-1]\n",
        "feature_names = df_train.drop(columns=['labels']).columns\n",
        "\n",
        "plt.figure(figsize=(12, 6))\n",
        "plt.bar(range(20), importances_rf[indices_rf][:20], color=\"teal\")\n",
        "plt.xticks(range(20), feature_names[indices_rf][:20], rotation=90)\n",
        "plt.title(\"Top 20 Features  Random Forest\")\n",
        "plt.show()\n",
        "\n",
        "\n",
        "\n",
        "# Gradient Boosting Feature Importance\n",
        "\n",
        "\n",
        "importances_gb = gb.feature_importances_\n",
        "indices_gb = np.argsort(importances_gb)[::-1]\n",
        "\n",
        "plt.figure(figsize=(12, 6))\n",
        "plt.bar(range(20), importances_gb[indices_gb][:20], color=\"orange\")\n",
        "plt.xticks(range(20), feature_names[indices_gb][:20], rotation=90)\n",
        "plt.title(\"Top 20 Features  Gradient Boosting\")\n",
        "plt.show()\n",
        "\n",
        "print(\"Feature importance plots completed.\")\n",
        "\n",
        "#The tuned models are used to extract feature importance scores.\n",
        "#Bar charts display the top 20 most influential features for each model.\n",
        "#This analysis helps interpret which network traffic characteristics contribute most to intrusion detection.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "1V1ukl7aX38H",
        "outputId": "9c73ee0a-b0ed-405a-fccb-0fbedf41ec88"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Number of classes: 37\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_ranking.py:1188: UndefinedMetricWarning: No positive samples in y_true, true positive value should be meaningless\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_ranking.py:379: UndefinedMetricWarning: Only one class is present in y_true. ROC AUC score is not defined in that case.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Random Forest ROC-AUC:\n",
            "Macro-AUC: nan\n",
            "Micro-AUC: 0.964887816850131\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_ranking.py:1188: UndefinedMetricWarning: No positive samples in y_true, true positive value should be meaningless\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_ranking.py:379: UndefinedMetricWarning: Only one class is present in y_true. ROC AUC score is not defined in that case.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Gradient Boosting ROC-AUC:\n",
            "Macro-AUC: nan\n",
            "Micro-AUC: 0.9458056834573524\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "ROC-AUC calculations complete!\n"
          ]
        }
      ],
      "source": [
        "\n",
        "# SECTION 9. ROC-AUC (MULTICLASS ONE-VS-REST)\n",
        "\n",
        "\n",
        "from sklearn.preprocessing import label_binarize\n",
        "from sklearn.metrics import roc_curve, auc\n",
        "import numpy as np # Ensure numpy is imported\n",
        "\n",
        "\n",
        "# 1. Prepare one-hot encoded y_test\n",
        "\n",
        "\n",
        "classes = label_encoder_y.classes_         # original class names\n",
        "n_classes = len(classes)\n",
        "\n",
        "y_test_bin = label_binarize(y_test, classes=range(n_classes))\n",
        "\n",
        "print(\"Number of classes:\", n_classes)\n",
        "\n",
        "\n",
        "\n",
        "# 2. Get probability predictions\n",
        "\n",
        "\n",
        "# Best Random Forest model from tuning\n",
        "best_rf_model = RandomForestClassifier(\n",
        "    n_estimators=grid_rf.best_params_['n_estimators'],\n",
        "    max_depth=grid_rf.best_params_['max_depth'],\n",
        "    max_features=grid_rf.best_params_['max_features'],\n",
        "    random_state=42,\n",
        "    n_jobs=-1\n",
        ")\n",
        "best_rf_model.fit(X_train, y_train)\n",
        "y_score_rf_raw = best_rf_model.predict_proba(X_test)\n",
        "\n",
        "# Create a full probability array for RF with n_classes columns\n",
        "y_score_rf = np.zeros((y_score_rf_raw.shape[0], n_classes))\n",
        "for i, class_label_val in enumerate(best_rf_model.classes_):\n",
        "    y_score_rf[:, class_label_val] = y_score_rf_raw[:, i]\n",
        "\n",
        "# Best Gradient Boosting model from tuning\n",
        "best_gb_model = GradientBoostingClassifier(\n",
        "    n_estimators=grid_gb.best_params_['n_estimators'],\n",
        "    learning_rate=grid_gb.best_params_['learning_rate'],\n",
        "    max_depth=grid_gb.best_params_['max_depth'],\n",
        "    random_state=42\n",
        ")\n",
        "best_gb_model.fit(X_train, y_train)\n",
        "y_score_gb_raw = best_gb_model.predict_proba(X_test)\n",
        "\n",
        "# Create a full probability array for GB with n_classes columns\n",
        "y_score_gb = np.zeros((y_score_gb_raw.shape[0], n_classes))\n",
        "for i, class_label_val in enumerate(best_gb_model.classes_):\n",
        "    y_score_gb[:, class_label_val] = y_score_gb_raw[:, i]\n",
        "\n",
        "\n",
        "\n",
        "# 3. Compute ROC curve (Random Forest)\n",
        "\n",
        "\n",
        "fpr_rf = dict()\n",
        "tpr_rf = dict()\n",
        "roc_auc_rf = dict()\n",
        "\n",
        "for i in range(n_classes):\n",
        "    fpr_rf[i], tpr_rf[i], _ = roc_curve(y_test_bin[:, i], y_score_rf[:, i])\n",
        "    roc_auc_rf[i] = auc(fpr_rf[i], tpr_rf[i])\n",
        "\n",
        "# Macro & Micro\n",
        "macro_auc_rf = roc_auc_score(y_test_bin, y_score_rf, average=\"macro\", multi_class=\"ovr\")\n",
        "micro_auc_rf = roc_auc_score(y_test_bin, y_score_rf, average=\"micro\", multi_class=\"ovr\")\n",
        "\n",
        "print(\"\\nRandom Forest ROC-AUC:\")\n",
        "print(\"Macro-AUC:\", macro_auc_rf)\n",
        "print(\"Micro-AUC:\", micro_auc_rf)\n",
        "\n",
        "\n",
        "\n",
        "# 4. Plot ROC curves for 3 example classes\n",
        "\n",
        "\n",
        "plt.figure(figsize=(8, 6))\n",
        "\n",
        "example_classes = [0, 1, 2]  # first three classes for clarity\n",
        "\n",
        "for i in example_classes:\n",
        "    plt.plot(fpr_rf[i], tpr_rf[i], label=f\"Class {classes[i]} (AUC={roc_auc_rf[i]:.2f})\")\n",
        "\n",
        "plt.plot([0,1], [0,1], 'k--')\n",
        "plt.title(\"ROC Curve (Random Forest)\")\n",
        "plt.xlabel(\"False Positive Rate\")\n",
        "plt.ylabel(\"True Positive Rate\")\n",
        "plt.legend()\n",
        "plt.show()\n",
        "\n",
        "\n",
        "\n",
        "# 5. Compute ROC-AUC for Gradient Boosting\n",
        "\n",
        "\n",
        "fpr_gb = dict()\n",
        "tpr_gb = dict()\n",
        "roc_auc_gb = dict()\n",
        "\n",
        "for i in range(n_classes):\n",
        "    fpr_gb[i], tpr_gb[i], _ = roc_curve(y_test_bin[:, i], y_score_gb[:, i])\n",
        "    roc_auc_gb[i] = auc(fpr_gb[i], tpr_gb[i])\n",
        "\n",
        "macro_auc_gb = roc_auc_score(y_test_bin, y_score_gb, average=\"macro\", multi_class=\"ovr\")\n",
        "micro_auc_gb = roc_auc_score(y_test_bin, y_score_gb, average=\"micro\", multi_class=\"ovr\")\n",
        "\n",
        "print(\"\\nGradient Boosting ROC-AUC:\")\n",
        "print(\"Macro-AUC:\", macro_auc_gb)\n",
        "print(\"Micro-AUC:\", micro_auc_gb)\n",
        "\n",
        "\n",
        "\n",
        "# 6. Plot ROC curves for GB\n",
        "\n",
        "\n",
        "plt.figure(figsize=(8, 6))\n",
        "\n",
        "for i in example_classes:\n",
        "    plt.plot(fpr_gb[i], tpr_gb[i], label=f\"Class {classes[i]} (AUC={roc_auc_gb[i]:.2f})\")\n",
        "\n",
        "plt.plot([0,1], [0,1], 'k--')\n",
        "plt.title(\"ROC Curve (Gradient Boosting)\")\n",
        "plt.xlabel(\"False Positive Rate\")\n",
        "plt.ylabel(\"True Positive Rate\")\n",
        "plt.legend()\n",
        "plt.show()\n",
        "\n",
        "print(\"\\nROC-AUC calculations complete!\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "93YRyGoGYB5x",
        "outputId": "99c89a74-97b8-42a7-a4fb-c60150f07a7e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Random Forest (Tuned) RESULTS\n",
            "Training Time: 9.125s\n",
            "Prediction Time: 0.163s\n",
            "Accuracy: 0.9139\n",
            "Precision: 0.8703\n",
            "Recall: 0.9139\n",
            "F1 Score: 0.8766\n",
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.00      0.00      0.00       228\n",
            "           1       0.97      0.99      0.98       227\n",
            "           2       0.88      0.41      0.56        17\n",
            "           3       1.00      0.50      0.67         2\n",
            "           4       1.00      0.02      0.04       411\n",
            "           5       0.00      0.00      0.00        41\n",
            "           6       1.00      1.00      1.00         2\n",
            "           7       0.93      1.00      0.96       479\n",
            "           8       1.00      0.50      0.67         2\n",
            "           9       1.00      0.75      0.86         4\n",
            "          10       0.00      0.00      0.00        94\n",
            "          11       0.00      0.00      0.00       310\n",
            "          12       1.00      0.11      0.20         9\n",
            "          13       0.00      0.00      0.00         2\n",
            "          14       0.99      1.00      1.00      6654\n",
            "          15       1.00      0.99      1.00       206\n",
            "          16       0.87      0.99      0.93     11245\n",
            "          17       1.00      1.00      1.00         1\n",
            "          18       1.00      1.00      1.00         1\n",
            "          19       0.89      0.94      0.92        35\n",
            "          20       0.96      1.00      0.98       371\n",
            "          21       0.00      0.00      0.00       211\n",
            "          22       0.00      0.00      0.00         9\n",
            "          23       1.00      0.25      0.40         4\n",
            "          24       0.00      0.00      0.00        93\n",
            "          25       0.85      1.00      0.92       698\n",
            "          26       0.00      0.00      0.00         8\n",
            "          27       0.99      1.00      1.00       540\n",
            "          28       0.00      0.00      0.00        43\n",
            "          29       0.00      0.00      0.00        99\n",
            "          31       0.89      1.00      0.94       104\n",
            "          32       1.00      1.00      1.00       107\n",
            "          33       0.75      0.01      0.02       279\n",
            "          34       0.00      0.00      0.00         4\n",
            "          35       0.00      0.00      0.00         1\n",
            "          36       0.00      0.00      0.00         3\n",
            "\n",
            "    accuracy                           0.91     22544\n",
            "   macro avg       0.58      0.46      0.47     22544\n",
            "weighted avg       0.87      0.91      0.88     22544\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Gradient Boosting (Tuned) RESULTS\n",
            "Training Time: 111.220s\n",
            "Prediction Time: 0.164s\n",
            "Accuracy: 0.9076\n",
            "Precision: 0.8607\n",
            "Recall: 0.9076\n",
            "F1 Score: 0.8725\n",
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.00      0.00      0.00       228\n",
            "           1       0.61      0.99      0.75       227\n",
            "           2       0.83      0.29      0.43        17\n",
            "           3       0.40      1.00      0.57         2\n",
            "           4       1.00      0.05      0.10       411\n",
            "           5       0.00      0.00      0.00        41\n",
            "           6       0.50      1.00      0.67         2\n",
            "           7       0.98      0.96      0.97       479\n",
            "           8       1.00      1.00      1.00         2\n",
            "           9       0.02      0.25      0.04         4\n",
            "          10       0.00      0.00      0.00        94\n",
            "          11       0.00      0.00      0.00       310\n",
            "          12       0.00      0.00      0.00         9\n",
            "          13       0.00      0.00      0.00         2\n",
            "          14       0.99      1.00      0.99      6654\n",
            "          15       0.82      0.81      0.81       206\n",
            "          16       0.88      0.99      0.93     11245\n",
            "          17       0.00      0.00      0.00         1\n",
            "          18       1.00      1.00      1.00         1\n",
            "          19       0.89      0.97      0.93        35\n",
            "          20       0.95      0.98      0.96       371\n",
            "          21       0.00      0.00      0.00       211\n",
            "          22       0.00      0.00      0.00         9\n",
            "          23       0.08      0.25      0.12         4\n",
            "          24       0.00      0.00      0.00        93\n",
            "          25       0.86      0.99      0.92       698\n",
            "          26       0.00      0.00      0.00         8\n",
            "          27       0.98      1.00      0.99       540\n",
            "          28       0.00      0.00      0.00        43\n",
            "          29       0.00      0.00      0.00        99\n",
            "          31       0.89      1.00      0.94       104\n",
            "          32       0.98      0.89      0.93       107\n",
            "          33       0.27      0.01      0.02       279\n",
            "          34       0.00      0.00      0.00         4\n",
            "          35       0.00      0.00      0.00         1\n",
            "          36       0.00      0.00      0.00         3\n",
            "\n",
            "    accuracy                           0.91     22544\n",
            "   macro avg       0.41      0.43      0.39     22544\n",
            "weighted avg       0.86      0.91      0.87     22544\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "                       Model  Training Time  Prediction Time  Accuracy  \\\n",
              "0      Random Forest (Tuned)       9.124720         0.162767  0.913946   \n",
              "1  Gradient Boosting (Tuned)     111.220317         0.163523  0.907603   \n",
              "\n",
              "   Precision    Recall  F1 Score  Macro AUC  Micro AUC  \n",
              "0   0.870336  0.913946  0.876550        NaN   0.964888  \n",
              "1   0.860736  0.907603  0.872502        NaN   0.945806  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e91b3168-abc3-4849-a5d2-f9371fdccd3e\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Model</th>\n",
              "      <th>Training Time</th>\n",
              "      <th>Prediction Time</th>\n",
              "      <th>Accuracy</th>\n",
              "      <th>Precision</th>\n",
              "      <th>Recall</th>\n",
              "      <th>F1 Score</th>\n",
              "      <th>Macro AUC</th>\n",
              "      <th>Micro AUC</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Random Forest (Tuned)</td>\n",
              "      <td>9.124720</td>\n",
              "      <td>0.162767</td>\n",
              "      <td>0.913946</td>\n",
              "      <td>0.870336</td>\n",
              "      <td>0.913946</td>\n",
              "      <td>0.876550</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.964888</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Gradient Boosting (Tuned)</td>\n",
              "      <td>111.220317</td>\n",
              "      <td>0.163523</td>\n",
              "      <td>0.907603</td>\n",
              "      <td>0.860736</td>\n",
              "      <td>0.907603</td>\n",
              "      <td>0.872502</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.945806</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-e91b3168-abc3-4849-a5d2-f9371fdccd3e')\"\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-e91b3168-abc3-4849-a5d2-f9371fdccd3e 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-e91b3168-abc3-4849-a5d2-f9371fdccd3e');\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-5788bd39-f796-4cc4-9565-a958191969eb\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-5788bd39-f796-4cc4-9565-a958191969eb')\"\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-5788bd39-f796-4cc4-9565-a958191969eb button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "  <div id=\"id_66b4161a-2424-400c-9296-1fa81e568157\">\n",
              "    <style>\n",
              "      .colab-df-generate {\n",
              "        background-color: #E8F0FE;\n",
              "        border: none;\n",
              "        border-radius: 50%;\n",
              "        cursor: pointer;\n",
              "        display: none;\n",
              "        fill: #1967D2;\n",
              "        height: 32px;\n",
              "        padding: 0 0 0 0;\n",
              "        width: 32px;\n",
              "      }\n",
              "\n",
              "      .colab-df-generate:hover {\n",
              "        background-color: #E2EBFA;\n",
              "        box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "        fill: #174EA6;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate:hover {\n",
              "        background-color: #434B5C;\n",
              "        box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "        filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "        fill: #FFFFFF;\n",
              "      }\n",
              "    </style>\n",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('final_df')\"\n",
              "            title=\"Generate code using this dataframe.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_66b4161a-2424-400c-9296-1fa81e568157 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('final_df');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "final_df",
              "summary": "{\n  \"name\": \"final_df\",\n  \"rows\": 2,\n  \"fields\": [\n    {\n      \"column\": \"Model\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"Gradient Boosting (Tuned)\",\n          \"Random Forest (Tuned)\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Training Time\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 72.19248915689313,\n        \"min\": 9.124719858169556,\n        \"max\": 111.22031712532043,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          111.22031712532043,\n          9.124719858169556\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Prediction Time\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0005349278013002671,\n        \"min\": 0.162766695022583,\n        \"max\": 0.16352319717407227,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.16352319717407227,\n          0.162766695022583\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Accuracy\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.004485285207136134,\n        \"min\": 0.9076029098651526,\n        \"max\": 0.9139460610361959,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.9076029098651526,\n          0.9139460610361959\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Precision\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.006788508505461814,\n        \"min\": 0.8607356530311849,\n        \"max\": 0.8703360538278941,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.8607356530311849,\n          0.8703360538278941\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Recall\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.004485285207136134,\n        \"min\": 0.9076029098651526,\n        \"max\": 0.9139460610361959,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.9076029098651526,\n          0.9139460610361959\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"F1 Score\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.002862841003230488,\n        \"min\": 0.8725016354284754,\n        \"max\": 0.8765503040021617,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.8725016354284754,\n          0.8765503040021617\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Macro AUC\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": null,\n        \"min\": null,\n        \"max\": null,\n        \"num_unique_values\": 0,\n        \"samples\": [],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Micro AUC\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.01349310592154004,\n        \"min\": 0.9458056834573524,\n        \"max\": 0.964887816850131,\n        \"num_unique_values\": 2,\n        \"samples\": [],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Final comparison table generated successfully\n"
          ]
        }
      ],
      "source": [
        "\n",
        "# SECTION 10. FINAL COMPARISON TABLE\n",
        "\n",
        "\n",
        "# Evaluate tuned RF\n",
        "tuned_rf_results, _ = evaluate_model(\n",
        "    \"Random Forest (Tuned)\",\n",
        "    best_rf_model,\n",
        "    X_train,\n",
        "    X_test,\n",
        "    y_train,\n",
        "    y_test\n",
        ")\n",
        "\n",
        "# Evaluate tuned GB\n",
        "tuned_gb_results, _ = evaluate_model(\n",
        "    \"Gradient Boosting (Tuned)\",\n",
        "    best_gb_model,\n",
        "    X_train,\n",
        "    X_test,\n",
        "    y_train,\n",
        "    y_test\n",
        ")\n",
        "\n",
        "# Add ROC-AUC values\n",
        "tuned_rf_results[\"Macro AUC\"] = macro_auc_rf\n",
        "tuned_rf_results[\"Micro AUC\"] = micro_auc_rf\n",
        "\n",
        "tuned_gb_results[\"Macro AUC\"] = macro_auc_gb\n",
        "tuned_gb_results[\"Micro AUC\"] = micro_auc_gb\n",
        "\n",
        "# Create DataFrame\n",
        "final_df = pd.DataFrame([tuned_rf_results, tuned_gb_results])\n",
        "\n",
        "display(final_df)\n",
        "\n",
        "print(\"\\nFinal comparison table generated successfully\")\n",
        "\n",
        "#A summary table is created to compare both tuned models across all metrics.\n",
        "#It includes accuracy, precision, recall, F1-score, training time, prediction time, and ROC-AUC.\n",
        "#This table supports the final discussion and helps justify which model performs best and why.\n"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}