DBSCAN_Clustering_.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "DBSCAN Clustering .ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "mount_file_id": "1Sk5d1F3FtwSm2sWB0OftMjADatCoxl_h",
      "authorship_tag": "ABX9TyP4HwQco4XQZ/t70c6sABMd",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/krish-hayagriva/Machine-Learning-Projects/blob/main/DBSCAN_Clustering_.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "This sheet contains the program code for performing clustering on Wine data using DBSCAN Algorithim "
      ],
      "metadata": {
        "id": "MOKgBsC1OYZh"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Importing Libraries"
      ],
      "metadata": {
        "id": "oRj98Zo8OoCj"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "P9OWqOHmyqds"
      },
      "outputs": [],
      "source": [
        "import pandas as pd"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import scipy as sp\n",
        "import sklearn as scikit\n",
        "import plotly.express as px"
      ],
      "metadata": {
        "id": "G-tJEvuB0FxH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pip install -U scikit-learn"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OzqqP9qg06DO",
        "outputId": "0905ad1c-0dd2-446b-ade3-644b17eecd7e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.7/dist-packages (1.0.2)\n",
            "Requirement already satisfied: scipy>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn) (1.4.1)\n",
            "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from scikit-learn) (1.1.0)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn) (3.1.0)\n",
            "Requirement already satisfied: numpy>=1.14.6 in /usr/local/lib/python3.7/dist-packages (from scikit-learn) (1.21.5)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Importing and reading the dataset"
      ],
      "metadata": {
        "id": "bdESkARnOgv2"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IJRKr52EPt27",
        "outputId": "a9cd2551-6907-46d6-9676-115edc48431b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "wine = pd.read_csv(\"/content/drive/My Drive/wine.csv\")\n"
      ],
      "metadata": {
        "id": "F-KoIVFhQsr0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Reading the rice dataframe"
      ],
      "metadata": {
        "id": "sVx0u499RaBZ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "wine\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "YAXCeJmRa22q",
        "outputId": "a1e3d5d0-0447-407e-bea2-cdfe93405c20"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     alcohol  malic   ash  alcanity  magn  phenols  flavnoids  nonfph  procy  \\\n",
              "0      14.23   1.71  2.43      15.6   127     2.80       3.06    0.28   2.29   \n",
              "1      13.20   1.78  2.14      11.2   100     2.65       2.76    0.26   1.28   \n",
              "2      13.16   2.36  2.67      18.6   101     2.80       3.24    0.30   2.81   \n",
              "3      14.37   1.95  2.50      16.8   113     3.85       3.49    0.24   2.18   \n",
              "4      13.24   2.59  2.87      21.0   118     2.80       2.69    0.39   1.82   \n",
              "..       ...    ...   ...       ...   ...      ...        ...     ...    ...   \n",
              "173    13.71   5.65  2.45      20.5    95     1.68       0.61    0.52   1.06   \n",
              "174    13.40   3.91  2.48      23.0   102     1.80       0.75    0.43   1.41   \n",
              "175    13.27   4.28  2.26      20.0   120     1.59       0.69    0.43   1.35   \n",
              "176    13.17   2.59  2.37      20.0   120     1.65       0.68    0.53   1.46   \n",
              "177    14.13   4.10  2.74      24.5    96     2.05       0.76    0.56   1.35   \n",
              "\n",
              "     cintensity   hue  od280  proline  \n",
              "0          5.64  1.04   3.92     1065  \n",
              "1          4.38  1.05   3.40     1050  \n",
              "2          5.68  1.03   3.17     1185  \n",
              "3          7.80  0.86   3.45     1480  \n",
              "4          4.32  1.04   2.93      735  \n",
              "..          ...   ...    ...      ...  \n",
              "173        7.70  0.64   1.74      740  \n",
              "174        7.30  0.70   1.56      750  \n",
              "175       10.20  0.59   1.56      835  \n",
              "176        9.30  0.60   1.62      840  \n",
              "177        9.20  0.61   1.60      560  \n",
              "\n",
              "[178 rows x 13 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-1b00d14e-36a7-40b4-be17-1dd961fe5ff8\">\n",
              "    <div 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>alcohol</th>\n",
              "      <th>malic</th>\n",
              "      <th>ash</th>\n",
              "      <th>alcanity</th>\n",
              "      <th>magn</th>\n",
              "      <th>phenols</th>\n",
              "      <th>flavnoids</th>\n",
              "      <th>nonfph</th>\n",
              "      <th>procy</th>\n",
              "      <th>cintensity</th>\n",
              "      <th>hue</th>\n",
              "      <th>od280</th>\n",
              "      <th>proline</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>14.23</td>\n",
              "      <td>1.71</td>\n",
              "      <td>2.43</td>\n",
              "      <td>15.6</td>\n",
              "      <td>127</td>\n",
              "      <td>2.80</td>\n",
              "      <td>3.06</td>\n",
              "      <td>0.28</td>\n",
              "      <td>2.29</td>\n",
              "      <td>5.64</td>\n",
              "      <td>1.04</td>\n",
              "      <td>3.92</td>\n",
              "      <td>1065</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>13.20</td>\n",
              "      <td>1.78</td>\n",
              "      <td>2.14</td>\n",
              "      <td>11.2</td>\n",
              "      <td>100</td>\n",
              "      <td>2.65</td>\n",
              "      <td>2.76</td>\n",
              "      <td>0.26</td>\n",
              "      <td>1.28</td>\n",
              "      <td>4.38</td>\n",
              "      <td>1.05</td>\n",
              "      <td>3.40</td>\n",
              "      <td>1050</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>13.16</td>\n",
              "      <td>2.36</td>\n",
              "      <td>2.67</td>\n",
              "      <td>18.6</td>\n",
              "      <td>101</td>\n",
              "      <td>2.80</td>\n",
              "      <td>3.24</td>\n",
              "      <td>0.30</td>\n",
              "      <td>2.81</td>\n",
              "      <td>5.68</td>\n",
              "      <td>1.03</td>\n",
              "      <td>3.17</td>\n",
              "      <td>1185</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>14.37</td>\n",
              "      <td>1.95</td>\n",
              "      <td>2.50</td>\n",
              "      <td>16.8</td>\n",
              "      <td>113</td>\n",
              "      <td>3.85</td>\n",
              "      <td>3.49</td>\n",
              "      <td>0.24</td>\n",
              "      <td>2.18</td>\n",
              "      <td>7.80</td>\n",
              "      <td>0.86</td>\n",
              "      <td>3.45</td>\n",
              "      <td>1480</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>13.24</td>\n",
              "      <td>2.59</td>\n",
              "      <td>2.87</td>\n",
              "      <td>21.0</td>\n",
              "      <td>118</td>\n",
              "      <td>2.80</td>\n",
              "      <td>2.69</td>\n",
              "      <td>0.39</td>\n",
              "      <td>1.82</td>\n",
              "      <td>4.32</td>\n",
              "      <td>1.04</td>\n",
              "      <td>2.93</td>\n",
              "      <td>735</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>173</th>\n",
              "      <td>13.71</td>\n",
              "      <td>5.65</td>\n",
              "      <td>2.45</td>\n",
              "      <td>20.5</td>\n",
              "      <td>95</td>\n",
              "      <td>1.68</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.52</td>\n",
              "      <td>1.06</td>\n",
              "      <td>7.70</td>\n",
              "      <td>0.64</td>\n",
              "      <td>1.74</td>\n",
              "      <td>740</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>174</th>\n",
              "      <td>13.40</td>\n",
              "      <td>3.91</td>\n",
              "      <td>2.48</td>\n",
              "      <td>23.0</td>\n",
              "      <td>102</td>\n",
              "      <td>1.80</td>\n",
              "      <td>0.75</td>\n",
              "      <td>0.43</td>\n",
              "      <td>1.41</td>\n",
              "      <td>7.30</td>\n",
              "      <td>0.70</td>\n",
              "      <td>1.56</td>\n",
              "      <td>750</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>175</th>\n",
              "      <td>13.27</td>\n",
              "      <td>4.28</td>\n",
              "      <td>2.26</td>\n",
              "      <td>20.0</td>\n",
              "      <td>120</td>\n",
              "      <td>1.59</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.43</td>\n",
              "      <td>1.35</td>\n",
              "      <td>10.20</td>\n",
              "      <td>0.59</td>\n",
              "      <td>1.56</td>\n",
              "      <td>835</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>176</th>\n",
              "      <td>13.17</td>\n",
              "      <td>2.59</td>\n",
              "      <td>2.37</td>\n",
              "      <td>20.0</td>\n",
              "      <td>120</td>\n",
              "      <td>1.65</td>\n",
              "      <td>0.68</td>\n",
              "      <td>0.53</td>\n",
              "      <td>1.46</td>\n",
              "      <td>9.30</td>\n",
              "      <td>0.60</td>\n",
              "      <td>1.62</td>\n",
              "      <td>840</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>177</th>\n",
              "      <td>14.13</td>\n",
              "      <td>4.10</td>\n",
              "      <td>2.74</td>\n",
              "      <td>24.5</td>\n",
              "      <td>96</td>\n",
              "      <td>2.05</td>\n",
              "      <td>0.76</td>\n",
              "      <td>0.56</td>\n",
              "      <td>1.35</td>\n",
              "      <td>9.20</td>\n",
              "      <td>0.61</td>\n",
              "      <td>1.60</td>\n",
              "      <td>560</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>178 rows × 13 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1b00d14e-36a7-40b4-be17-1dd961fe5ff8')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-1b00d14e-36a7-40b4-be17-1dd961fe5ff8 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-1b00d14e-36a7-40b4-be17-1dd961fe5ff8');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "wine.isnull().sum()"
      ],
      "metadata": {
        "id": "kiPEj030YZM6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b3dfc0bf-74e3-470f-a6ee-6e8e9cf9aed8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "alcohol       0\n",
              "malic         0\n",
              "ash           0\n",
              "alcanity      0\n",
              "magn          0\n",
              "phenols       0\n",
              "flavnoids     0\n",
              "nonfph        0\n",
              "procy         0\n",
              "cintensity    0\n",
              "hue           0\n",
              "od280         0\n",
              "proline       0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "wine.info()"
      ],
      "metadata": {
        "id": "Wj0MfoIxq7J4",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "30a398f9-307c-4367-f545-96ea08263317"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 178 entries, 0 to 177\n",
            "Data columns (total 13 columns):\n",
            " #   Column      Non-Null Count  Dtype  \n",
            "---  ------      --------------  -----  \n",
            " 0   alcohol     178 non-null    float64\n",
            " 1   malic       178 non-null    float64\n",
            " 2   ash         178 non-null    float64\n",
            " 3   alcanity    178 non-null    float64\n",
            " 4   magn        178 non-null    int64  \n",
            " 5   phenols     178 non-null    float64\n",
            " 6   flavnoids   178 non-null    float64\n",
            " 7   nonfph      178 non-null    float64\n",
            " 8   procy       178 non-null    float64\n",
            " 9   cintensity  178 non-null    float64\n",
            " 10  hue         178 non-null    float64\n",
            " 11  od280       178 non-null    float64\n",
            " 12  proline     178 non-null    int64  \n",
            "dtypes: float64(11), int64(2)\n",
            "memory usage: 18.2 KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "wine.describe()"
      ],
      "metadata": {
        "id": "cA3P9ErSrVPw",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 364
        },
        "outputId": "631b6c63-4631-41b4-a003-be63355517ce"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "          alcohol       malic         ash    alcanity        magn     phenols  \\\n",
              "count  178.000000  178.000000  178.000000  178.000000  178.000000  178.000000   \n",
              "mean    13.000618    2.336348    2.366517   19.494944   99.741573    2.295112   \n",
              "std      0.811827    1.117146    0.274344    3.339564   14.282484    0.625851   \n",
              "min     11.030000    0.740000    1.360000   10.600000   70.000000    0.980000   \n",
              "25%     12.362500    1.602500    2.210000   17.200000   88.000000    1.742500   \n",
              "50%     13.050000    1.865000    2.360000   19.500000   98.000000    2.355000   \n",
              "75%     13.677500    3.082500    2.557500   21.500000  107.000000    2.800000   \n",
              "max     14.830000    5.800000    3.230000   30.000000  162.000000    3.880000   \n",
              "\n",
              "        flavnoids      nonfph       procy  cintensity         hue       od280  \\\n",
              "count  178.000000  178.000000  178.000000  178.000000  178.000000  178.000000   \n",
              "mean     2.029270    0.361854    1.590899    5.058090    0.957449    2.611685   \n",
              "std      0.998859    0.124453    0.572359    2.318286    0.228572    0.709990   \n",
              "min      0.340000    0.130000    0.410000    1.280000    0.480000    1.270000   \n",
              "25%      1.205000    0.270000    1.250000    3.220000    0.782500    1.937500   \n",
              "50%      2.135000    0.340000    1.555000    4.690000    0.965000    2.780000   \n",
              "75%      2.875000    0.437500    1.950000    6.200000    1.120000    3.170000   \n",
              "max      5.080000    0.660000    3.580000   13.000000    1.710000    4.000000   \n",
              "\n",
              "           proline  \n",
              "count   178.000000  \n",
              "mean    746.893258  \n",
              "std     314.907474  \n",
              "min     278.000000  \n",
              "25%     500.500000  \n",
              "50%     673.500000  \n",
              "75%     985.000000  \n",
              "max    1680.000000  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a9083446-c5a6-41a8-84b0-99a53548fdba\">\n",
              "    <div 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>alcohol</th>\n",
              "      <th>malic</th>\n",
              "      <th>ash</th>\n",
              "      <th>alcanity</th>\n",
              "      <th>magn</th>\n",
              "      <th>phenols</th>\n",
              "      <th>flavnoids</th>\n",
              "      <th>nonfph</th>\n",
              "      <th>procy</th>\n",
              "      <th>cintensity</th>\n",
              "      <th>hue</th>\n",
              "      <th>od280</th>\n",
              "      <th>proline</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "      <td>178.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>13.000618</td>\n",
              "      <td>2.336348</td>\n",
              "      <td>2.366517</td>\n",
              "      <td>19.494944</td>\n",
              "      <td>99.741573</td>\n",
              "      <td>2.295112</td>\n",
              "      <td>2.029270</td>\n",
              "      <td>0.361854</td>\n",
              "      <td>1.590899</td>\n",
              "      <td>5.058090</td>\n",
              "      <td>0.957449</td>\n",
              "      <td>2.611685</td>\n",
              "      <td>746.893258</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>0.811827</td>\n",
              "      <td>1.117146</td>\n",
              "      <td>0.274344</td>\n",
              "      <td>3.339564</td>\n",
              "      <td>14.282484</td>\n",
              "      <td>0.625851</td>\n",
              "      <td>0.998859</td>\n",
              "      <td>0.124453</td>\n",
              "      <td>0.572359</td>\n",
              "      <td>2.318286</td>\n",
              "      <td>0.228572</td>\n",
              "      <td>0.709990</td>\n",
              "      <td>314.907474</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>11.030000</td>\n",
              "      <td>0.740000</td>\n",
              "      <td>1.360000</td>\n",
              "      <td>10.600000</td>\n",
              "      <td>70.000000</td>\n",
              "      <td>0.980000</td>\n",
              "      <td>0.340000</td>\n",
              "      <td>0.130000</td>\n",
              "      <td>0.410000</td>\n",
              "      <td>1.280000</td>\n",
              "      <td>0.480000</td>\n",
              "      <td>1.270000</td>\n",
              "      <td>278.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>12.362500</td>\n",
              "      <td>1.602500</td>\n",
              "      <td>2.210000</td>\n",
              "      <td>17.200000</td>\n",
              "      <td>88.000000</td>\n",
              "      <td>1.742500</td>\n",
              "      <td>1.205000</td>\n",
              "      <td>0.270000</td>\n",
              "      <td>1.250000</td>\n",
              "      <td>3.220000</td>\n",
              "      <td>0.782500</td>\n",
              "      <td>1.937500</td>\n",
              "      <td>500.500000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>13.050000</td>\n",
              "      <td>1.865000</td>\n",
              "      <td>2.360000</td>\n",
              "      <td>19.500000</td>\n",
              "      <td>98.000000</td>\n",
              "      <td>2.355000</td>\n",
              "      <td>2.135000</td>\n",
              "      <td>0.340000</td>\n",
              "      <td>1.555000</td>\n",
              "      <td>4.690000</td>\n",
              "      <td>0.965000</td>\n",
              "      <td>2.780000</td>\n",
              "      <td>673.500000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>13.677500</td>\n",
              "      <td>3.082500</td>\n",
              "      <td>2.557500</td>\n",
              "      <td>21.500000</td>\n",
              "      <td>107.000000</td>\n",
              "      <td>2.800000</td>\n",
              "      <td>2.875000</td>\n",
              "      <td>0.437500</td>\n",
              "      <td>1.950000</td>\n",
              "      <td>6.200000</td>\n",
              "      <td>1.120000</td>\n",
              "      <td>3.170000</td>\n",
              "      <td>985.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>14.830000</td>\n",
              "      <td>5.800000</td>\n",
              "      <td>3.230000</td>\n",
              "      <td>30.000000</td>\n",
              "      <td>162.000000</td>\n",
              "      <td>3.880000</td>\n",
              "      <td>5.080000</td>\n",
              "      <td>0.660000</td>\n",
              "      <td>3.580000</td>\n",
              "      <td>13.000000</td>\n",
              "      <td>1.710000</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>1680.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a9083446-c5a6-41a8-84b0-99a53548fdba')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-a9083446-c5a6-41a8-84b0-99a53548fdba 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-a9083446-c5a6-41a8-84b0-99a53548fdba');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn import preprocessing\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "sclr = StandardScaler() # defining the standard scaler\n",
        "winet = pd.DataFrame(sclr.fit_transform(wine),columns =wine.columns) # transforming all features into a standardized form\n",
        "(winet).head(5)"
      ],
      "metadata": {
        "id": "emIjmTfotCN1",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 270
        },
        "outputId": "c10753f0-4f20-4aba-db19-0212f11ed841"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    alcohol     malic       ash  alcanity      magn   phenols  flavnoids  \\\n",
              "0  1.518613 -0.562250  0.232053 -1.169593  1.913905  0.808997   1.034819   \n",
              "1  0.246290 -0.499413 -0.827996 -2.490847  0.018145  0.568648   0.733629   \n",
              "2  0.196879  0.021231  1.109334 -0.268738  0.088358  0.808997   1.215533   \n",
              "3  1.691550 -0.346811  0.487926 -0.809251  0.930918  2.491446   1.466525   \n",
              "4  0.295700  0.227694  1.840403  0.451946  1.281985  0.808997   0.663351   \n",
              "\n",
              "     nonfph     procy  cintensity       hue     od280   proline  \n",
              "0 -0.659563  1.224884    0.251717  0.362177  1.847920  1.013009  \n",
              "1 -0.820719 -0.544721   -0.293321  0.406051  1.113449  0.965242  \n",
              "2 -0.498407  2.135968    0.269020  0.318304  0.788587  1.395148  \n",
              "3 -0.981875  1.032155    1.186068 -0.427544  1.184071  2.334574  \n",
              "4  0.226796  0.401404   -0.319276  0.362177  0.449601 -0.037874  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-16138fb1-1a8a-4542-9501-0caf4027cef5\">\n",
              "    <div 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>alcohol</th>\n",
              "      <th>malic</th>\n",
              "      <th>ash</th>\n",
              "      <th>alcanity</th>\n",
              "      <th>magn</th>\n",
              "      <th>phenols</th>\n",
              "      <th>flavnoids</th>\n",
              "      <th>nonfph</th>\n",
              "      <th>procy</th>\n",
              "      <th>cintensity</th>\n",
              "      <th>hue</th>\n",
              "      <th>od280</th>\n",
              "      <th>proline</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1.518613</td>\n",
              "      <td>-0.562250</td>\n",
              "      <td>0.232053</td>\n",
              "      <td>-1.169593</td>\n",
              "      <td>1.913905</td>\n",
              "      <td>0.808997</td>\n",
              "      <td>1.034819</td>\n",
              "      <td>-0.659563</td>\n",
              "      <td>1.224884</td>\n",
              "      <td>0.251717</td>\n",
              "      <td>0.362177</td>\n",
              "      <td>1.847920</td>\n",
              "      <td>1.013009</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.246290</td>\n",
              "      <td>-0.499413</td>\n",
              "      <td>-0.827996</td>\n",
              "      <td>-2.490847</td>\n",
              "      <td>0.018145</td>\n",
              "      <td>0.568648</td>\n",
              "      <td>0.733629</td>\n",
              "      <td>-0.820719</td>\n",
              "      <td>-0.544721</td>\n",
              "      <td>-0.293321</td>\n",
              "      <td>0.406051</td>\n",
              "      <td>1.113449</td>\n",
              "      <td>0.965242</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.196879</td>\n",
              "      <td>0.021231</td>\n",
              "      <td>1.109334</td>\n",
              "      <td>-0.268738</td>\n",
              "      <td>0.088358</td>\n",
              "      <td>0.808997</td>\n",
              "      <td>1.215533</td>\n",
              "      <td>-0.498407</td>\n",
              "      <td>2.135968</td>\n",
              "      <td>0.269020</td>\n",
              "      <td>0.318304</td>\n",
              "      <td>0.788587</td>\n",
              "      <td>1.395148</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1.691550</td>\n",
              "      <td>-0.346811</td>\n",
              "      <td>0.487926</td>\n",
              "      <td>-0.809251</td>\n",
              "      <td>0.930918</td>\n",
              "      <td>2.491446</td>\n",
              "      <td>1.466525</td>\n",
              "      <td>-0.981875</td>\n",
              "      <td>1.032155</td>\n",
              "      <td>1.186068</td>\n",
              "      <td>-0.427544</td>\n",
              "      <td>1.184071</td>\n",
              "      <td>2.334574</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.295700</td>\n",
              "      <td>0.227694</td>\n",
              "      <td>1.840403</td>\n",
              "      <td>0.451946</td>\n",
              "      <td>1.281985</td>\n",
              "      <td>0.808997</td>\n",
              "      <td>0.663351</td>\n",
              "      <td>0.226796</td>\n",
              "      <td>0.401404</td>\n",
              "      <td>-0.319276</td>\n",
              "      <td>0.362177</td>\n",
              "      <td>0.449601</td>\n",
              "      <td>-0.037874</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-16138fb1-1a8a-4542-9501-0caf4027cef5')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-16138fb1-1a8a-4542-9501-0caf4027cef5 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-16138fb1-1a8a-4542-9501-0caf4027cef5');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "corr_matrix = winet.corr()\n",
        "print(corr_matrix)\n",
        "type(winet)"
      ],
      "metadata": {
        "id": "6aBSM4gpoolX",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "82609fc5-810f-4ec4-fb03-c3e72d51b211"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "             alcohol     malic       ash  alcanity      magn   phenols  \\\n",
            "alcohol     1.000000  0.094397  0.211545 -0.310235  0.270798  0.289101   \n",
            "malic       0.094397  1.000000  0.164045  0.288500 -0.054575 -0.335167   \n",
            "ash         0.211545  0.164045  1.000000  0.443367  0.286587  0.128980   \n",
            "alcanity   -0.310235  0.288500  0.443367  1.000000 -0.083333 -0.321113   \n",
            "magn        0.270798 -0.054575  0.286587 -0.083333  1.000000  0.214401   \n",
            "phenols     0.289101 -0.335167  0.128980 -0.321113  0.214401  1.000000   \n",
            "flavnoids   0.236815 -0.411007  0.115077 -0.351370  0.195784  0.864564   \n",
            "nonfph     -0.155929  0.292977  0.186230  0.361922 -0.256294 -0.449935   \n",
            "procy       0.136698 -0.220746  0.009652 -0.197327  0.236441  0.612413   \n",
            "cintensity  0.546364  0.248985  0.258887  0.018732  0.199950 -0.055136   \n",
            "hue        -0.071747 -0.561296 -0.074667 -0.273955  0.055398  0.433681   \n",
            "od280       0.072343 -0.368710  0.003911 -0.276769  0.066004  0.699949   \n",
            "proline     0.643720 -0.192011  0.223626 -0.440597  0.393351  0.498115   \n",
            "\n",
            "            flavnoids    nonfph     procy  cintensity       hue     od280  \\\n",
            "alcohol      0.236815 -0.155929  0.136698    0.546364 -0.071747  0.072343   \n",
            "malic       -0.411007  0.292977 -0.220746    0.248985 -0.561296 -0.368710   \n",
            "ash          0.115077  0.186230  0.009652    0.258887 -0.074667  0.003911   \n",
            "alcanity    -0.351370  0.361922 -0.197327    0.018732 -0.273955 -0.276769   \n",
            "magn         0.195784 -0.256294  0.236441    0.199950  0.055398  0.066004   \n",
            "phenols      0.864564 -0.449935  0.612413   -0.055136  0.433681  0.699949   \n",
            "flavnoids    1.000000 -0.537900  0.652692   -0.172379  0.543479  0.787194   \n",
            "nonfph      -0.537900  1.000000 -0.365845    0.139057 -0.262640 -0.503270   \n",
            "procy        0.652692 -0.365845  1.000000   -0.025250  0.295544  0.519067   \n",
            "cintensity  -0.172379  0.139057 -0.025250    1.000000 -0.521813 -0.428815   \n",
            "hue          0.543479 -0.262640  0.295544   -0.521813  1.000000  0.565468   \n",
            "od280        0.787194 -0.503270  0.519067   -0.428815  0.565468  1.000000   \n",
            "proline      0.494193 -0.311385  0.330417    0.316100  0.236183  0.312761   \n",
            "\n",
            "             proline  \n",
            "alcohol     0.643720  \n",
            "malic      -0.192011  \n",
            "ash         0.223626  \n",
            "alcanity   -0.440597  \n",
            "magn        0.393351  \n",
            "phenols     0.498115  \n",
            "flavnoids   0.494193  \n",
            "nonfph     -0.311385  \n",
            "procy       0.330417  \n",
            "cintensity  0.316100  \n",
            "hue         0.236183  \n",
            "od280       0.312761  \n",
            "proline     1.000000  \n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "pandas.core.frame.DataFrame"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.cluster import DBSCAN\n",
        "from sklearn import metrics\n",
        "from sklearn.datasets import make_blobs\n"
      ],
      "metadata": {
        "id": "e9jfL_lWbtSH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# as in the K-Means algorithim implemented on wine data and it was found that K =3 was the most optimal no of clusters\n",
        "wdb = DBSCAN(eps= 2.96,min_samples=5,metric ='euclidean',leaf_size = 30)\n",
        "w_dbcs = wdb.fit(winet)\n",
        "wlabel= (wdb.labels_)\n",
        "wlabel"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DbbWS7gmFiNi",
        "outputId": "f3298338-0f15-4d5e-823b-6b7a27777951"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([ 0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0,  0,  0,  0, -1,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0, -1,  0,  0,  0, -1,  0,  0,  0,  0, -1,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0,  0,  0,  0,  0,  0, -1, -1,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0,  0,  0,  0, -1,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0, -1,  0,  0, -1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0, -1, -1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
              "        0,  0,  0,  0,  0,  0,  0,  0])"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# appending cluster ID to wine data frame.\n",
        "wine['cluster_id'] = wlabel\n",
        "wine"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "bsDHPkNNRIoD",
        "outputId": "7baf7304-daf0-47c6-bb02-a268bb19836f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     alcohol  malic   ash  alcanity  magn  phenols  flavnoids  nonfph  procy  \\\n",
              "0      14.23   1.71  2.43      15.6   127     2.80       3.06    0.28   2.29   \n",
              "1      13.20   1.78  2.14      11.2   100     2.65       2.76    0.26   1.28   \n",
              "2      13.16   2.36  2.67      18.6   101     2.80       3.24    0.30   2.81   \n",
              "3      14.37   1.95  2.50      16.8   113     3.85       3.49    0.24   2.18   \n",
              "4      13.24   2.59  2.87      21.0   118     2.80       2.69    0.39   1.82   \n",
              "..       ...    ...   ...       ...   ...      ...        ...     ...    ...   \n",
              "173    13.71   5.65  2.45      20.5    95     1.68       0.61    0.52   1.06   \n",
              "174    13.40   3.91  2.48      23.0   102     1.80       0.75    0.43   1.41   \n",
              "175    13.27   4.28  2.26      20.0   120     1.59       0.69    0.43   1.35   \n",
              "176    13.17   2.59  2.37      20.0   120     1.65       0.68    0.53   1.46   \n",
              "177    14.13   4.10  2.74      24.5    96     2.05       0.76    0.56   1.35   \n",
              "\n",
              "     cintensity   hue  od280  proline  cluster_id  \n",
              "0          5.64  1.04   3.92     1065           0  \n",
              "1          4.38  1.05   3.40     1050           0  \n",
              "2          5.68  1.03   3.17     1185           0  \n",
              "3          7.80  0.86   3.45     1480           0  \n",
              "4          4.32  1.04   2.93      735           0  \n",
              "..          ...   ...    ...      ...         ...  \n",
              "173        7.70  0.64   1.74      740           0  \n",
              "174        7.30  0.70   1.56      750           0  \n",
              "175       10.20  0.59   1.56      835           0  \n",
              "176        9.30  0.60   1.62      840           0  \n",
              "177        9.20  0.61   1.60      560           0  \n",
              "\n",
              "[178 rows x 14 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-9ec03659-40ce-458f-85fb-2ca8fe1cbefe\">\n",
              "    <div 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>alcohol</th>\n",
              "      <th>malic</th>\n",
              "      <th>ash</th>\n",
              "      <th>alcanity</th>\n",
              "      <th>magn</th>\n",
              "      <th>phenols</th>\n",
              "      <th>flavnoids</th>\n",
              "      <th>nonfph</th>\n",
              "      <th>procy</th>\n",
              "      <th>cintensity</th>\n",
              "      <th>hue</th>\n",
              "      <th>od280</th>\n",
              "      <th>proline</th>\n",
              "      <th>cluster_id</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>14.23</td>\n",
              "      <td>1.71</td>\n",
              "      <td>2.43</td>\n",
              "      <td>15.6</td>\n",
              "      <td>127</td>\n",
              "      <td>2.80</td>\n",
              "      <td>3.06</td>\n",
              "      <td>0.28</td>\n",
              "      <td>2.29</td>\n",
              "      <td>5.64</td>\n",
              "      <td>1.04</td>\n",
              "      <td>3.92</td>\n",
              "      <td>1065</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>13.20</td>\n",
              "      <td>1.78</td>\n",
              "      <td>2.14</td>\n",
              "      <td>11.2</td>\n",
              "      <td>100</td>\n",
              "      <td>2.65</td>\n",
              "      <td>2.76</td>\n",
              "      <td>0.26</td>\n",
              "      <td>1.28</td>\n",
              "      <td>4.38</td>\n",
              "      <td>1.05</td>\n",
              "      <td>3.40</td>\n",
              "      <td>1050</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>13.16</td>\n",
              "      <td>2.36</td>\n",
              "      <td>2.67</td>\n",
              "      <td>18.6</td>\n",
              "      <td>101</td>\n",
              "      <td>2.80</td>\n",
              "      <td>3.24</td>\n",
              "      <td>0.30</td>\n",
              "      <td>2.81</td>\n",
              "      <td>5.68</td>\n",
              "      <td>1.03</td>\n",
              "      <td>3.17</td>\n",
              "      <td>1185</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>14.37</td>\n",
              "      <td>1.95</td>\n",
              "      <td>2.50</td>\n",
              "      <td>16.8</td>\n",
              "      <td>113</td>\n",
              "      <td>3.85</td>\n",
              "      <td>3.49</td>\n",
              "      <td>0.24</td>\n",
              "      <td>2.18</td>\n",
              "      <td>7.80</td>\n",
              "      <td>0.86</td>\n",
              "      <td>3.45</td>\n",
              "      <td>1480</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>13.24</td>\n",
              "      <td>2.59</td>\n",
              "      <td>2.87</td>\n",
              "      <td>21.0</td>\n",
              "      <td>118</td>\n",
              "      <td>2.80</td>\n",
              "      <td>2.69</td>\n",
              "      <td>0.39</td>\n",
              "      <td>1.82</td>\n",
              "      <td>4.32</td>\n",
              "      <td>1.04</td>\n",
              "      <td>2.93</td>\n",
              "      <td>735</td>\n",
              "      <td>0</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>173</th>\n",
              "      <td>13.71</td>\n",
              "      <td>5.65</td>\n",
              "      <td>2.45</td>\n",
              "      <td>20.5</td>\n",
              "      <td>95</td>\n",
              "      <td>1.68</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.52</td>\n",
              "      <td>1.06</td>\n",
              "      <td>7.70</td>\n",
              "      <td>0.64</td>\n",
              "      <td>1.74</td>\n",
              "      <td>740</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>174</th>\n",
              "      <td>13.40</td>\n",
              "      <td>3.91</td>\n",
              "      <td>2.48</td>\n",
              "      <td>23.0</td>\n",
              "      <td>102</td>\n",
              "      <td>1.80</td>\n",
              "      <td>0.75</td>\n",
              "      <td>0.43</td>\n",
              "      <td>1.41</td>\n",
              "      <td>7.30</td>\n",
              "      <td>0.70</td>\n",
              "      <td>1.56</td>\n",
              "      <td>750</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>175</th>\n",
              "      <td>13.27</td>\n",
              "      <td>4.28</td>\n",
              "      <td>2.26</td>\n",
              "      <td>20.0</td>\n",
              "      <td>120</td>\n",
              "      <td>1.59</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.43</td>\n",
              "      <td>1.35</td>\n",
              "      <td>10.20</td>\n",
              "      <td>0.59</td>\n",
              "      <td>1.56</td>\n",
              "      <td>835</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>176</th>\n",
              "      <td>13.17</td>\n",
              "      <td>2.59</td>\n",
              "      <td>2.37</td>\n",
              "      <td>20.0</td>\n",
              "      <td>120</td>\n",
              "      <td>1.65</td>\n",
              "      <td>0.68</td>\n",
              "      <td>0.53</td>\n",
              "      <td>1.46</td>\n",
              "      <td>9.30</td>\n",
              "      <td>0.60</td>\n",
              "      <td>1.62</td>\n",
              "      <td>840</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>177</th>\n",
              "      <td>14.13</td>\n",
              "      <td>4.10</td>\n",
              "      <td>2.74</td>\n",
              "      <td>24.5</td>\n",
              "      <td>96</td>\n",
              "      <td>2.05</td>\n",
              "      <td>0.76</td>\n",
              "      <td>0.56</td>\n",
              "      <td>1.35</td>\n",
              "      <td>9.20</td>\n",
              "      <td>0.61</td>\n",
              "      <td>1.60</td>\n",
              "      <td>560</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>178 rows × 14 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9ec03659-40ce-458f-85fb-2ca8fe1cbefe')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-9ec03659-40ce-458f-85fb-2ca8fe1cbefe 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-9ec03659-40ce-458f-85fb-2ca8fe1cbefe');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "n_noise_ = list(wlabel).count(-1)\n",
        "print(\"Estimated number of noise points: %d\" % n_noise_)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lBvb5sSCVqu0",
        "outputId": "55eb8aef-d140-477f-f896-f7fdd602fbd3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Estimated number of noise points: 11\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn import metrics\n",
        "metrics.silhouette_score(winet,labels = wlabel, metric = 'euclidean')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wL-ePQFziyc2",
        "outputId": "c5e6bbb2-181e-4362-f7ba-2300b4ee2d75"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.21836446281240493"
            ]
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(wlabel)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QTMzCdGi-WcJ",
        "outputId": "f964a0d0-e5ca-45c8-f9c8-c24d9e462639"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[ 0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0\n",
            "  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0\n",
            "  0  0  0  0  0  0  0  0  0  0  0 -1  0  0  0  0  0  0  0  0  0 -1  0  0\n",
            "  0 -1  0  0  0  0 -1  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0 -1\n",
            " -1  0  0  0  0  0  0  0  0  0  0  0  0  0 -1  0  0  0  0  0  0  0  0  0\n",
            "  0 -1  0  0 -1  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0\n",
            "  0  0  0  0  0  0  0  0  0  0  0  0  0  0 -1 -1  0  0  0  0  0  0  0  0\n",
            "  0  0  0  0  0  0  0  0  0  0]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn import metrics\n",
        "shil_Averagescore = metrics.silhouette_score(winet, labels = wlabel, metric = 'euclidean')\n",
        "print(shil_Averagescore)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vwaPwCl7SEsj",
        "outputId": "9dc03d69-5727-4196-b589-0ae9e2b126f6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.21836446281240493\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "A Silhoutte score lies between -1 and +1 . Towards +1 , the larger the value, higher is the density of clustering and towards zero or -1 indicating incorrect clustering or that data is by itself a single cluster. \n",
        "\n",
        "In the extant case, our Silhouttee score is positive and 0.21 indicating relatively correct clustering and reasonable density."
      ],
      "metadata": {
        "id": "KEMuQqBcXO2V"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "We see that the DBSACN is not the most appropriate method as it assigns most of the data to a single cluster unlike in K Means where it extracted 3 clusters based on the K Means centroid."
      ],
      "metadata": {
        "id": "DR_xlwK-SvUY"
      }
    }
  ]
}