Classifying_safe_and_dangerous_water.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "#Description about dataset\n",
        "A water safety data set is a set of data that contains information about the water quality of different sampling points. This data set typically includes parameters such as pH, alkalinity, hardness, total dissolved solids, nitrate content, coliform content, etc.\n",
        "\n",
        "Water safety data sets are used to assess water quality. If the data set shows that the water quality parameters are within the permissible limits, then the water is considered safe. On the other hand, if the water quality parameters exceed the permissible limits, then the water may not be safe and needs to be treated before use."
      ],
      "metadata": {
        "id": "m_pof5LKNsPX"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import seaborn as sns\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.svm import SVC\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "from sklearn.metrics import ConfusionMatrixDisplay\n",
        "from sklearn.metrics import classification_report\n",
        "from sklearn import metrics"
      ],
      "metadata": {
        "id": "DidskyptOZRz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(\"waterQuality1.csv\")"
      ],
      "metadata": {
        "id": "pgZEt4AdOdZh"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 255
        },
        "id": "pCEWpgkAOqt_",
        "outputId": "0573d17e-13ca-4c61-d5b7-777f30125b52"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   aluminium ammonia  arsenic  barium  cadmium  chloramine  chromium  copper  \\\n",
              "0       1.65    9.08     0.04    2.85    0.007        0.35      0.83    0.17   \n",
              "1       2.32   21.16     0.01    3.31    0.002        5.28      0.68    0.66   \n",
              "2       1.01   14.02     0.04    0.58    0.008        4.24      0.53    0.02   \n",
              "3       1.36   11.33     0.04    2.96    0.001        7.23      0.03    1.66   \n",
              "4       0.92   24.33     0.03    0.20    0.006        2.67      0.69    0.57   \n",
              "\n",
              "   flouride  bacteria  ...   lead  nitrates  nitrites  mercury  perchlorate  \\\n",
              "0      0.05      0.20  ...  0.054     16.08      1.13    0.007        37.75   \n",
              "1      0.90      0.65  ...  0.100      2.01      1.93    0.003        32.26   \n",
              "2      0.99      0.05  ...  0.078     14.16      1.11    0.006        50.28   \n",
              "3      1.08      0.71  ...  0.016      1.41      1.29    0.004         9.12   \n",
              "4      0.61      0.13  ...  0.117      6.74      1.11    0.003        16.90   \n",
              "\n",
              "   radium  selenium  silver  uranium  is_safe  \n",
              "0    6.78      0.08    0.34     0.02        1  \n",
              "1    3.21      0.08    0.27     0.05        1  \n",
              "2    7.07      0.07    0.44     0.01        0  \n",
              "3    1.72      0.02    0.45     0.05        1  \n",
              "4    2.41      0.02    0.06     0.02        1  \n",
              "\n",
              "[5 rows x 21 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-90d34c4c-050e-4076-925f-f93bc1b32f63\" 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>aluminium</th>\n",
              "      <th>ammonia</th>\n",
              "      <th>arsenic</th>\n",
              "      <th>barium</th>\n",
              "      <th>cadmium</th>\n",
              "      <th>chloramine</th>\n",
              "      <th>chromium</th>\n",
              "      <th>copper</th>\n",
              "      <th>flouride</th>\n",
              "      <th>bacteria</th>\n",
              "      <th>...</th>\n",
              "      <th>lead</th>\n",
              "      <th>nitrates</th>\n",
              "      <th>nitrites</th>\n",
              "      <th>mercury</th>\n",
              "      <th>perchlorate</th>\n",
              "      <th>radium</th>\n",
              "      <th>selenium</th>\n",
              "      <th>silver</th>\n",
              "      <th>uranium</th>\n",
              "      <th>is_safe</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1.65</td>\n",
              "      <td>9.08</td>\n",
              "      <td>0.04</td>\n",
              "      <td>2.85</td>\n",
              "      <td>0.007</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.83</td>\n",
              "      <td>0.17</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.20</td>\n",
              "      <td>...</td>\n",
              "      <td>0.054</td>\n",
              "      <td>16.08</td>\n",
              "      <td>1.13</td>\n",
              "      <td>0.007</td>\n",
              "      <td>37.75</td>\n",
              "      <td>6.78</td>\n",
              "      <td>0.08</td>\n",
              "      <td>0.34</td>\n",
              "      <td>0.02</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2.32</td>\n",
              "      <td>21.16</td>\n",
              "      <td>0.01</td>\n",
              "      <td>3.31</td>\n",
              "      <td>0.002</td>\n",
              "      <td>5.28</td>\n",
              "      <td>0.68</td>\n",
              "      <td>0.66</td>\n",
              "      <td>0.90</td>\n",
              "      <td>0.65</td>\n",
              "      <td>...</td>\n",
              "      <td>0.100</td>\n",
              "      <td>2.01</td>\n",
              "      <td>1.93</td>\n",
              "      <td>0.003</td>\n",
              "      <td>32.26</td>\n",
              "      <td>3.21</td>\n",
              "      <td>0.08</td>\n",
              "      <td>0.27</td>\n",
              "      <td>0.05</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1.01</td>\n",
              "      <td>14.02</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.58</td>\n",
              "      <td>0.008</td>\n",
              "      <td>4.24</td>\n",
              "      <td>0.53</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.99</td>\n",
              "      <td>0.05</td>\n",
              "      <td>...</td>\n",
              "      <td>0.078</td>\n",
              "      <td>14.16</td>\n",
              "      <td>1.11</td>\n",
              "      <td>0.006</td>\n",
              "      <td>50.28</td>\n",
              "      <td>7.07</td>\n",
              "      <td>0.07</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1.36</td>\n",
              "      <td>11.33</td>\n",
              "      <td>0.04</td>\n",
              "      <td>2.96</td>\n",
              "      <td>0.001</td>\n",
              "      <td>7.23</td>\n",
              "      <td>0.03</td>\n",
              "      <td>1.66</td>\n",
              "      <td>1.08</td>\n",
              "      <td>0.71</td>\n",
              "      <td>...</td>\n",
              "      <td>0.016</td>\n",
              "      <td>1.41</td>\n",
              "      <td>1.29</td>\n",
              "      <td>0.004</td>\n",
              "      <td>9.12</td>\n",
              "      <td>1.72</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.45</td>\n",
              "      <td>0.05</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.92</td>\n",
              "      <td>24.33</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.20</td>\n",
              "      <td>0.006</td>\n",
              "      <td>2.67</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.57</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.13</td>\n",
              "      <td>...</td>\n",
              "      <td>0.117</td>\n",
              "      <td>6.74</td>\n",
              "      <td>1.11</td>\n",
              "      <td>0.003</td>\n",
              "      <td>16.90</td>\n",
              "      <td>2.41</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.06</td>\n",
              "      <td>0.02</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 21 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-90d34c4c-050e-4076-925f-f93bc1b32f63')\"\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-90d34c4c-050e-4076-925f-f93bc1b32f63 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-90d34c4c-050e-4076-925f-f93bc1b32f63');\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-dfef9359-1b0b-4fdb-a44f-10329640dcc0\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-dfef9359-1b0b-4fdb-a44f-10329640dcc0')\"\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-dfef9359-1b0b-4fdb-a44f-10329640dcc0 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# is_safe - class attribute {0 - not safe, 1 - safe}"
      ],
      "metadata": {
        "id": "P6Xa3kx_OuIr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(4.3, 2.8))\n",
        "sns.countplot(data=df, x='is_safe');"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 296
        },
        "id": "XZ3eeq5GQ20H",
        "outputId": "5970fc08-3edf-4ec0-da8e-732bcef8906e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 430x280 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df[pd.to_numeric(df['is_safe'], errors='coerce').notnull()]"
      ],
      "metadata": {
        "id": "WAfdHPc5Rq2m"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(4.3, 2.8))\n",
        "sns.countplot(data=df, x='is_safe');"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 296
        },
        "id": "zPq8ivXFRq4_",
        "outputId": "d41a91bf-ea8c-4f27-829f-2c7a9454187d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 430x280 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y = df['is_safe']\n",
        "X = df.drop('is_safe', axis=1)"
      ],
      "metadata": {
        "id": "83_cWdZPRq_E"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 443
        },
        "id": "7yvQ1oiLTPV0",
        "outputId": "6d1c0fa6-5b56-4d50-d5a3-16948623fb5c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      aluminium ammonia  arsenic  barium  cadmium  chloramine  chromium  \\\n",
              "0          1.65    9.08     0.04    2.85    0.007        0.35      0.83   \n",
              "1          2.32   21.16     0.01    3.31    0.002        5.28      0.68   \n",
              "2          1.01   14.02     0.04    0.58    0.008        4.24      0.53   \n",
              "3          1.36   11.33     0.04    2.96    0.001        7.23      0.03   \n",
              "4          0.92   24.33     0.03    0.20    0.006        2.67      0.69   \n",
              "...         ...     ...      ...     ...      ...         ...       ...   \n",
              "7994       0.05    7.78     0.00    1.95    0.040        0.10      0.03   \n",
              "7995       0.05   24.22     0.02    0.59    0.010        0.45      0.02   \n",
              "7996       0.09    6.85     0.00    0.61    0.030        0.05      0.05   \n",
              "7997       0.01      10     0.01    2.00    0.000        2.00      0.00   \n",
              "7998       0.04    6.85     0.01    0.70    0.030        0.05      0.01   \n",
              "\n",
              "      copper  flouride  bacteria  viruses   lead  nitrates  nitrites  mercury  \\\n",
              "0       0.17      0.05      0.20    0.000  0.054     16.08      1.13    0.007   \n",
              "1       0.66      0.90      0.65    0.650  0.100      2.01      1.93    0.003   \n",
              "2       0.02      0.99      0.05    0.003  0.078     14.16      1.11    0.006   \n",
              "3       1.66      1.08      0.71    0.710  0.016      1.41      1.29    0.004   \n",
              "4       0.57      0.61      0.13    0.001  0.117      6.74      1.11    0.003   \n",
              "...      ...       ...       ...      ...    ...       ...       ...      ...   \n",
              "7994    0.03      1.37      0.00    0.000  0.197     14.29      1.00    0.005   \n",
              "7995    0.02      1.48      0.00    0.000  0.031     10.27      1.00    0.001   \n",
              "7996    0.02      0.91      0.00    0.000  0.182     15.92      1.00    0.000   \n",
              "7997    0.09      0.00      0.00    0.000  0.000      0.00      0.00    0.000   \n",
              "7998    0.03      1.00      0.00    0.000  0.182     15.92      1.00    0.000   \n",
              "\n",
              "      perchlorate  radium  selenium  silver  uranium  \n",
              "0           37.75    6.78      0.08    0.34     0.02  \n",
              "1           32.26    3.21      0.08    0.27     0.05  \n",
              "2           50.28    7.07      0.07    0.44     0.01  \n",
              "3            9.12    1.72      0.02    0.45     0.05  \n",
              "4           16.90    2.41      0.02    0.06     0.02  \n",
              "...           ...     ...       ...     ...      ...  \n",
              "7994         3.57    2.13      0.09    0.06     0.03  \n",
              "7995         1.48    1.11      0.09    0.10     0.08  \n",
              "7996         1.35    4.84      0.00    0.04     0.05  \n",
              "7997         0.00    0.00      0.00    0.00     0.00  \n",
              "7998         1.35    4.84      0.00    0.04     0.05  \n",
              "\n",
              "[7996 rows x 20 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a3ef2d0a-2cb0-4aa4-b1d6-7df7e0fb3b95\" 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>aluminium</th>\n",
              "      <th>ammonia</th>\n",
              "      <th>arsenic</th>\n",
              "      <th>barium</th>\n",
              "      <th>cadmium</th>\n",
              "      <th>chloramine</th>\n",
              "      <th>chromium</th>\n",
              "      <th>copper</th>\n",
              "      <th>flouride</th>\n",
              "      <th>bacteria</th>\n",
              "      <th>viruses</th>\n",
              "      <th>lead</th>\n",
              "      <th>nitrates</th>\n",
              "      <th>nitrites</th>\n",
              "      <th>mercury</th>\n",
              "      <th>perchlorate</th>\n",
              "      <th>radium</th>\n",
              "      <th>selenium</th>\n",
              "      <th>silver</th>\n",
              "      <th>uranium</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1.65</td>\n",
              "      <td>9.08</td>\n",
              "      <td>0.04</td>\n",
              "      <td>2.85</td>\n",
              "      <td>0.007</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.83</td>\n",
              "      <td>0.17</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.20</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.054</td>\n",
              "      <td>16.08</td>\n",
              "      <td>1.13</td>\n",
              "      <td>0.007</td>\n",
              "      <td>37.75</td>\n",
              "      <td>6.78</td>\n",
              "      <td>0.08</td>\n",
              "      <td>0.34</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2.32</td>\n",
              "      <td>21.16</td>\n",
              "      <td>0.01</td>\n",
              "      <td>3.31</td>\n",
              "      <td>0.002</td>\n",
              "      <td>5.28</td>\n",
              "      <td>0.68</td>\n",
              "      <td>0.66</td>\n",
              "      <td>0.90</td>\n",
              "      <td>0.65</td>\n",
              "      <td>0.650</td>\n",
              "      <td>0.100</td>\n",
              "      <td>2.01</td>\n",
              "      <td>1.93</td>\n",
              "      <td>0.003</td>\n",
              "      <td>32.26</td>\n",
              "      <td>3.21</td>\n",
              "      <td>0.08</td>\n",
              "      <td>0.27</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1.01</td>\n",
              "      <td>14.02</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.58</td>\n",
              "      <td>0.008</td>\n",
              "      <td>4.24</td>\n",
              "      <td>0.53</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.99</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.003</td>\n",
              "      <td>0.078</td>\n",
              "      <td>14.16</td>\n",
              "      <td>1.11</td>\n",
              "      <td>0.006</td>\n",
              "      <td>50.28</td>\n",
              "      <td>7.07</td>\n",
              "      <td>0.07</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1.36</td>\n",
              "      <td>11.33</td>\n",
              "      <td>0.04</td>\n",
              "      <td>2.96</td>\n",
              "      <td>0.001</td>\n",
              "      <td>7.23</td>\n",
              "      <td>0.03</td>\n",
              "      <td>1.66</td>\n",
              "      <td>1.08</td>\n",
              "      <td>0.71</td>\n",
              "      <td>0.710</td>\n",
              "      <td>0.016</td>\n",
              "      <td>1.41</td>\n",
              "      <td>1.29</td>\n",
              "      <td>0.004</td>\n",
              "      <td>9.12</td>\n",
              "      <td>1.72</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.45</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.92</td>\n",
              "      <td>24.33</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.20</td>\n",
              "      <td>0.006</td>\n",
              "      <td>2.67</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.57</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.13</td>\n",
              "      <td>0.001</td>\n",
              "      <td>0.117</td>\n",
              "      <td>6.74</td>\n",
              "      <td>1.11</td>\n",
              "      <td>0.003</td>\n",
              "      <td>16.90</td>\n",
              "      <td>2.41</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.06</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7994</th>\n",
              "      <td>0.05</td>\n",
              "      <td>7.78</td>\n",
              "      <td>0.00</td>\n",
              "      <td>1.95</td>\n",
              "      <td>0.040</td>\n",
              "      <td>0.10</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.03</td>\n",
              "      <td>1.37</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.197</td>\n",
              "      <td>14.29</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.005</td>\n",
              "      <td>3.57</td>\n",
              "      <td>2.13</td>\n",
              "      <td>0.09</td>\n",
              "      <td>0.06</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7995</th>\n",
              "      <td>0.05</td>\n",
              "      <td>24.22</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.59</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.45</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.02</td>\n",
              "      <td>1.48</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.031</td>\n",
              "      <td>10.27</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.001</td>\n",
              "      <td>1.48</td>\n",
              "      <td>1.11</td>\n",
              "      <td>0.09</td>\n",
              "      <td>0.10</td>\n",
              "      <td>0.08</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7996</th>\n",
              "      <td>0.09</td>\n",
              "      <td>6.85</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.030</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.182</td>\n",
              "      <td>15.92</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>1.35</td>\n",
              "      <td>4.84</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7997</th>\n",
              "      <td>0.01</td>\n",
              "      <td>10</td>\n",
              "      <td>0.01</td>\n",
              "      <td>2.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>2.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.09</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7998</th>\n",
              "      <td>0.04</td>\n",
              "      <td>6.85</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.70</td>\n",
              "      <td>0.030</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.03</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.182</td>\n",
              "      <td>15.92</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>1.35</td>\n",
              "      <td>4.84</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>7996 rows × 20 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-a3ef2d0a-2cb0-4aa4-b1d6-7df7e0fb3b95')\"\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-a3ef2d0a-2cb0-4aa4-b1d6-7df7e0fb3b95 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-a3ef2d0a-2cb0-4aa4-b1d6-7df7e0fb3b95');\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-916d860a-efae-4e2e-abfb-5b23f8d1bf41\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-916d860a-efae-4e2e-abfb-5b23f8d1bf41')\"\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-916d860a-efae-4e2e-abfb-5b23f8d1bf41 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=101)"
      ],
      "metadata": {
        "id": "kZI5ynW4RrBN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "scaler = StandardScaler()"
      ],
      "metadata": {
        "id": "89gYKO3at1ei"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#scaler data"
      ],
      "metadata": {
        "id": "fQNQqvATg2td"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "scaled_X_train = scaler.fit_transform(X_train)\n",
        "scaled_X_test = scaler.transform(X_test)"
      ],
      "metadata": {
        "id": "AscThNtzRrG7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#USE SVM to Classifying"
      ],
      "metadata": {
        "id": "88OtW3uht9ll"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = SVC(class_weight='balanced', C = 10)\n",
        "# Parameter C controls the level of regularization of the model. The lower the C value, the higher the level of regularization."
      ],
      "metadata": {
        "id": "9aNNq29ARrJW"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "parameters = {\n",
        "    'C': [100, 150, 155, 160, 165, 170, 180, 190, 200],\n",
        "    'gamma': ['scale', 'auto']\n",
        "}\n",
        "# if gamma='scale' (default) is passed then it uses 1 / (n_features * X.var()) as value of gamma,\n",
        "# if ‘auto’, uses 1 / n_features"
      ],
      "metadata": {
        "id": "UJAcs4bvYqKX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "grid_model = GridSearchCV(model, parameters)\n",
        "# Hyperparameter tuning: Use GridSearchCV to choose the optimal value"
      ],
      "metadata": {
        "id": "YL9VSDq0ZzVe"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Optimization is the process of finding the optimal value for a function. In the context of machine learning, optimization is the process of finding the machine learning model that performs the best on the training dataset.\n",
        "\n",
        "There are many different optimization methods, each with its own advantages and disadvantages. Some common optimization methods include:\n",
        "\n",
        "* Gradient descent: This is the most basic optimization method, based on updating the model parameters in the direction opposite to the gradient of the loss function.\n",
        "\n",
        "* Stochastic gradient descent: This is a variation of gradient descent, which uses a small subset of the data to update the model parameters.\n",
        "\n",
        "* Newton's method: This is a more efficient optimization method than gradient descent, but it requires more computation.\n",
        "\n",
        "* Bayesian optimization: This is an optimization method based on Bayesian models, which uses the training data to estimate the distribution of the optimal parameter."
      ],
      "metadata": {
        "id": "HftZkJPqx28T"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "  grid_model.fit(scaled_X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 117
        },
        "id": "_XC7U0OfUHKr",
        "outputId": "b62e322c-a148-48a6-a889-1d5d750b94ed"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(estimator=SVC(C=10, class_weight='balanced'),\n",
              "             param_grid={'C': [100, 150, 155, 160, 165, 170, 180, 190, 200],\n",
              "                         'gamma': ['scale', 'auto']})"
            ],
            "text/html": [
              "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(estimator=SVC(C=10, class_weight=&#x27;balanced&#x27;),\n",
              "             param_grid={&#x27;C&#x27;: [100, 150, 155, 160, 165, 170, 180, 190, 200],\n",
              "                         &#x27;gamma&#x27;: [&#x27;scale&#x27;, &#x27;auto&#x27;]})</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(estimator=SVC(C=10, class_weight=&#x27;balanced&#x27;),\n",
              "             param_grid={&#x27;C&#x27;: [100, 150, 155, 160, 165, 170, 180, 190, 200],\n",
              "                         &#x27;gamma&#x27;: [&#x27;scale&#x27;, &#x27;auto&#x27;]})</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(C=10, class_weight=&#x27;balanced&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(C=10, class_weight=&#x27;balanced&#x27;)</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "The method used is Gradient Descent. Gradient descent is a basic optimization method, used to find the parameters of the model so that the loss function is minimized.\n",
        "\n",
        "In this case, the loss function is hinge loss, which is used to evaluate the performance of the SVC model. Gradient descent will update the parameters of SVC in the opposite direction of the gradient of the loss function. The gradient of the loss function is a vector that indicates the direction in which the loss function decreases most quickly. By updating the parameters in this direction, gradient descent will help the model learn to classify more accurately.\n",
        "\n",
        "Some advantages of gradient descent:\n",
        "\n",
        "* Ability to optimize the loss function: Gradient Descent helps to optimize the loss functions during model training. It searches for optimal parameters (weights) by following the opposite direction of the gradient of the loss function, thereby helping to minimize prediction errors.\n",
        "* Good performance with large data sets: Gradient Descent can efficiently handle large datasets with millions or even billions of data samples. It breaks the data into mini-batches to calculate the gradient, helping to save time and computational resources."
      ],
      "metadata": {
        "id": "Hxj7Ynebz7_P"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "grid_model.best_params_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TanmuakHUHND",
        "outputId": "cea6c056-9530-4359-d08d-8ae9247476ce"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'C': 160, 'gamma': 'scale'}"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = grid_model.predict(scaled_X_test)\n"
      ],
      "metadata": {
        "id": "QyDod9oKUHPf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(classification_report(y_test, y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1HFRA5n9UHRk",
        "outputId": "21503eb9-19aa-434a-c878-dfced30d8dd1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.97      0.97      0.97       703\n",
            "           1       0.79      0.75      0.77        97\n",
            "\n",
            "    accuracy                           0.95       800\n",
            "   macro avg       0.88      0.86      0.87       800\n",
            "weighted avg       0.95      0.95      0.95       800\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "score = grid_model.score(scaled_X_test, y_test)\n",
        "print(score)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "t5knx1VLt5Qa",
        "outputId": "b9e18237-ae88-4710-ac71-530be7c0cd86"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.94625\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "9Fc4WyquUHTo"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "vuZwTHOmFCNj"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "o7m1o0b8FCSd"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "\n",
        "def svm_loss(y_true, y_pred):\n",
        "\n",
        "    hinge_loss = tf.maximum(0.0, 1 - y_true * y_pred)\n",
        "    C = 1.0\n",
        "    weights = model.trainable_variables\n",
        "    reg_term = 0.5 * C * sum([tf.reduce_sum(tf.square(w)) for w in weights])\n",
        "    total_loss = tf.reduce_mean(hinge_loss) + reg_term\n",
        "    return total_loss\n",
        "\n",
        "model = tf.keras.models.Sequential([\n",
        "    tf.keras.layers.Dense(1, activation=None, use_bias=False)  # Linear SVM\n",
        "])\n",
        "\n",
        "model.compile(optimizer='adam', loss=svm_loss)\n",
        "model.fit(scaled_X_train, y_train, epochs=100)\n",
        "loss = model.evaluate(scaled_X_test, y_test)\n",
        "print(\"Loss:\", loss)\n"
      ],
      "metadata": {
        "id": "KxLx64gnEukX"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}