1_2_KNNClassification.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "1.2_KNNClassification.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyPGl99JXSPUU4Yx5nYsA99b",
      "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/rupeshsm/AndroidEmotionAPI/blob/master/1_2_KNNClassification.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E0CwttzI7_vL"
      },
      "source": [
        "<h1>Diabetes detection using KNN"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fXGHkJOq-Klm"
      },
      "source": [
        "# Importing Libreries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xiWrE4y07oqO"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3_ZPe9Z582yk"
      },
      "source": [
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "\n",
        "from sklearn.metrics import confusion_matrix\n",
        "from sklearn.metrics import f1_score\n",
        "from sklearn.metrics import  accuracy_score\n",
        "from sklearn.metrics import  classification_report"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-GJ6mPJw-TG_"
      },
      "source": [
        "# Load and Understand Data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_vu0crcU9jS0"
      },
      "source": [
        "dataset = pd.read_csv('diabetes.csv')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5P2A1rc091Cp",
        "outputId": "bef3fdf1-3c22-4351-e32d-142e12e50d65"
      },
      "source": [
        "print(len(dataset))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "768\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2xpgwSpJ_tcu",
        "outputId": "1d96dc79-db65-426a-dd02-07b4efff4ea9"
      },
      "source": [
        "dataset.shape"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(768, 9)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 225
        },
        "id": "u482OzcL_CUZ",
        "outputId": "61c746d8-2de5-498f-aaa5-c118ee750428"
      },
      "source": [
        "dataset.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Pregnancies</th>\n",
              "      <th>Glucose</th>\n",
              "      <th>BloodPressure</th>\n",
              "      <th>SkinThickness</th>\n",
              "      <th>Insulin</th>\n",
              "      <th>BMI</th>\n",
              "      <th>DiabetesPedigreeFunction</th>\n",
              "      <th>Age</th>\n",
              "      <th>Outcome</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>148</td>\n",
              "      <td>72</td>\n",
              "      <td>35</td>\n",
              "      <td>0</td>\n",
              "      <td>33.6</td>\n",
              "      <td>0.627</td>\n",
              "      <td>50</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>85</td>\n",
              "      <td>66</td>\n",
              "      <td>29</td>\n",
              "      <td>0</td>\n",
              "      <td>26.6</td>\n",
              "      <td>0.351</td>\n",
              "      <td>31</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>183</td>\n",
              "      <td>64</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>23.3</td>\n",
              "      <td>0.672</td>\n",
              "      <td>32</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>89</td>\n",
              "      <td>66</td>\n",
              "      <td>23</td>\n",
              "      <td>94</td>\n",
              "      <td>28.1</td>\n",
              "      <td>0.167</td>\n",
              "      <td>21</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>137</td>\n",
              "      <td>40</td>\n",
              "      <td>35</td>\n",
              "      <td>168</td>\n",
              "      <td>43.1</td>\n",
              "      <td>2.288</td>\n",
              "      <td>33</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Pregnancies  Glucose  BloodPressure  ...  DiabetesPedigreeFunction  Age  Outcome\n",
              "0            6      148             72  ...                     0.627   50        1\n",
              "1            1       85             66  ...                     0.351   31        0\n",
              "2            8      183             64  ...                     0.672   32        1\n",
              "3            1       89             66  ...                     0.167   21        0\n",
              "4            0      137             40  ...                     2.288   33        1\n",
              "\n",
              "[5 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BR8uuRHV_Yoj",
        "outputId": "e984ccfc-71b3-4039-aace-776ce9ca3b09"
      },
      "source": [
        "dataset.info()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 768 entries, 0 to 767\n",
            "Data columns (total 9 columns):\n",
            " #   Column                    Non-Null Count  Dtype  \n",
            "---  ------                    --------------  -----  \n",
            " 0   Pregnancies               768 non-null    int64  \n",
            " 1   Glucose                   768 non-null    int64  \n",
            " 2   BloodPressure             768 non-null    int64  \n",
            " 3   SkinThickness             768 non-null    int64  \n",
            " 4   Insulin                   768 non-null    int64  \n",
            " 5   BMI                       768 non-null    float64\n",
            " 6   DiabetesPedigreeFunction  768 non-null    float64\n",
            " 7   Age                       768 non-null    int64  \n",
            " 8   Outcome                   768 non-null    int64  \n",
            "dtypes: float64(2), int64(7)\n",
            "memory usage: 54.1 KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cCM-c0WhAgPD"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tUV6fP2VBTdB"
      },
      "source": [
        "# Preprocessing"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SJzv4FnFBD6T"
      },
      "source": [
        "replace_zero = [ 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin',\n",
        "       'BMI']"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "40MTqvFBB-eo",
        "outputId": "8a8cacef-d761-487a-d0c0-18e22b2e964e"
      },
      "source": [
        "replace_zero"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 225
        },
        "id": "onFADgqcB_Vd",
        "outputId": "c7ffbf77-273e-4b32-f1ab-5689fff40e62"
      },
      "source": [
        "for column in replace_zero:\n",
        "  dataset[column] = dataset[column].replace(0, np.NaN)\n",
        "\n",
        "dataset.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Pregnancies</th>\n",
              "      <th>Glucose</th>\n",
              "      <th>BloodPressure</th>\n",
              "      <th>SkinThickness</th>\n",
              "      <th>Insulin</th>\n",
              "      <th>BMI</th>\n",
              "      <th>DiabetesPedigreeFunction</th>\n",
              "      <th>Age</th>\n",
              "      <th>Outcome</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>148.0</td>\n",
              "      <td>72.0</td>\n",
              "      <td>35.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>33.6</td>\n",
              "      <td>0.627</td>\n",
              "      <td>50</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>85.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>29.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>26.6</td>\n",
              "      <td>0.351</td>\n",
              "      <td>31</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>183.0</td>\n",
              "      <td>64.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>23.3</td>\n",
              "      <td>0.672</td>\n",
              "      <td>32</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>89.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>23.0</td>\n",
              "      <td>94.0</td>\n",
              "      <td>28.1</td>\n",
              "      <td>0.167</td>\n",
              "      <td>21</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>137.0</td>\n",
              "      <td>40.0</td>\n",
              "      <td>35.0</td>\n",
              "      <td>168.0</td>\n",
              "      <td>43.1</td>\n",
              "      <td>2.288</td>\n",
              "      <td>33</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Pregnancies  Glucose  BloodPressure  ...  DiabetesPedigreeFunction  Age  Outcome\n",
              "0            6    148.0           72.0  ...                     0.627   50        1\n",
              "1            1     85.0           66.0  ...                     0.351   31        0\n",
              "2            8    183.0           64.0  ...                     0.672   32        1\n",
              "3            1     89.0           66.0  ...                     0.167   21        0\n",
              "4            0    137.0           40.0  ...                     2.288   33        1\n",
              "\n",
              "[5 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BkpvY09QC2nz"
      },
      "source": [
        "for column in replace_zero:\n",
        "  mean = int(dataset[column].mean(skipna = True))\n",
        "  dataset[column] = dataset[column].replace(np.NaN, mean)\n",
        "\n",
        "dataset = dataset.fillna(dataset.mean())"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 225
        },
        "id": "jnRNpPvKDGQT",
        "outputId": "898da53c-5936-413d-a049-31a22e5579a8"
      },
      "source": [
        "dataset.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Pregnancies</th>\n",
              "      <th>Glucose</th>\n",
              "      <th>BloodPressure</th>\n",
              "      <th>SkinThickness</th>\n",
              "      <th>Insulin</th>\n",
              "      <th>BMI</th>\n",
              "      <th>DiabetesPedigreeFunction</th>\n",
              "      <th>Age</th>\n",
              "      <th>Outcome</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>148.0</td>\n",
              "      <td>72.0</td>\n",
              "      <td>35.0</td>\n",
              "      <td>155.0</td>\n",
              "      <td>33.6</td>\n",
              "      <td>0.627</td>\n",
              "      <td>50</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>85.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>29.0</td>\n",
              "      <td>155.0</td>\n",
              "      <td>26.6</td>\n",
              "      <td>0.351</td>\n",
              "      <td>31</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>183.0</td>\n",
              "      <td>64.0</td>\n",
              "      <td>29.0</td>\n",
              "      <td>155.0</td>\n",
              "      <td>23.3</td>\n",
              "      <td>0.672</td>\n",
              "      <td>32</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>89.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>23.0</td>\n",
              "      <td>94.0</td>\n",
              "      <td>28.1</td>\n",
              "      <td>0.167</td>\n",
              "      <td>21</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>137.0</td>\n",
              "      <td>40.0</td>\n",
              "      <td>35.0</td>\n",
              "      <td>168.0</td>\n",
              "      <td>43.1</td>\n",
              "      <td>2.288</td>\n",
              "      <td>33</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Pregnancies  Glucose  BloodPressure  ...  DiabetesPedigreeFunction  Age  Outcome\n",
              "0            6    148.0           72.0  ...                     0.627   50        1\n",
              "1            1     85.0           66.0  ...                     0.351   31        0\n",
              "2            8    183.0           64.0  ...                     0.672   32        1\n",
              "3            1     89.0           66.0  ...                     0.167   21        0\n",
              "4            0    137.0           40.0  ...                     2.288   33        1\n",
              "\n",
              "[5 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 225
        },
        "id": "jtJSy7I9DP90",
        "outputId": "18b3d0d3-aba8-4fac-a891-9b96418a2905"
      },
      "source": [
        "for column in replace_zero:\n",
        "  mean = int(dataset[column].mean(skipna = True))\n",
        "  dataset[column] = dataset[column].replace(np.NaN, mean)\n",
        "dataset.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Pregnancies</th>\n",
              "      <th>Glucose</th>\n",
              "      <th>BloodPressure</th>\n",
              "      <th>SkinThickness</th>\n",
              "      <th>Insulin</th>\n",
              "      <th>BMI</th>\n",
              "      <th>DiabetesPedigreeFunction</th>\n",
              "      <th>Age</th>\n",
              "      <th>Outcome</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>148.0</td>\n",
              "      <td>72.0</td>\n",
              "      <td>35.0</td>\n",
              "      <td>155.0</td>\n",
              "      <td>33.6</td>\n",
              "      <td>0.627</td>\n",
              "      <td>50</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>85.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>29.0</td>\n",
              "      <td>155.0</td>\n",
              "      <td>26.6</td>\n",
              "      <td>0.351</td>\n",
              "      <td>31</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>183.0</td>\n",
              "      <td>64.0</td>\n",
              "      <td>29.0</td>\n",
              "      <td>155.0</td>\n",
              "      <td>23.3</td>\n",
              "      <td>0.672</td>\n",
              "      <td>32</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>89.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>23.0</td>\n",
              "      <td>94.0</td>\n",
              "      <td>28.1</td>\n",
              "      <td>0.167</td>\n",
              "      <td>21</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>137.0</td>\n",
              "      <td>40.0</td>\n",
              "      <td>35.0</td>\n",
              "      <td>168.0</td>\n",
              "      <td>43.1</td>\n",
              "      <td>2.288</td>\n",
              "      <td>33</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Pregnancies  Glucose  BloodPressure  ...  DiabetesPedigreeFunction  Age  Outcome\n",
              "0            6    148.0           72.0  ...                     0.627   50        1\n",
              "1            1     85.0           66.0  ...                     0.351   31        0\n",
              "2            8    183.0           64.0  ...                     0.672   32        1\n",
              "3            1     89.0           66.0  ...                     0.167   21        0\n",
              "4            0    137.0           40.0  ...                     2.288   33        1\n",
              "\n",
              "[5 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5_ckNJfbEHwq"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LE9TJgq9wfuy"
      },
      "source": [
        "# Split Dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UGTv_EHHwkeE"
      },
      "source": [
        "X = dataset.iloc[: , 0:8]\n",
        "y = dataset.iloc[:, 8]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ioNApfetw17w"
      },
      "source": [
        "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state = 0, test_size = 0.2)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "65dJLOv_xN1V",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 350
        },
        "outputId": "35b1bfd9-47d6-45cf-f213-74b81f5fa66c"
      },
      "source": [
        "dataset.describe().transpose()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "      <th>min</th>\n",
              "      <th>25%</th>\n",
              "      <th>50%</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Pregnancies</th>\n",
              "      <td>768.0</td>\n",
              "      <td>3.845052</td>\n",
              "      <td>3.369578</td>\n",
              "      <td>0.000</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>3.0000</td>\n",
              "      <td>6.00000</td>\n",
              "      <td>17.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Glucose</th>\n",
              "      <td>768.0</td>\n",
              "      <td>121.682292</td>\n",
              "      <td>30.435999</td>\n",
              "      <td>44.000</td>\n",
              "      <td>99.75000</td>\n",
              "      <td>117.0000</td>\n",
              "      <td>140.25000</td>\n",
              "      <td>199.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>BloodPressure</th>\n",
              "      <td>768.0</td>\n",
              "      <td>72.386719</td>\n",
              "      <td>12.096642</td>\n",
              "      <td>24.000</td>\n",
              "      <td>64.00000</td>\n",
              "      <td>72.0000</td>\n",
              "      <td>80.00000</td>\n",
              "      <td>122.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SkinThickness</th>\n",
              "      <td>768.0</td>\n",
              "      <td>29.108073</td>\n",
              "      <td>8.791221</td>\n",
              "      <td>7.000</td>\n",
              "      <td>25.00000</td>\n",
              "      <td>29.0000</td>\n",
              "      <td>32.00000</td>\n",
              "      <td>99.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Insulin</th>\n",
              "      <td>768.0</td>\n",
              "      <td>155.281250</td>\n",
              "      <td>85.021550</td>\n",
              "      <td>14.000</td>\n",
              "      <td>121.50000</td>\n",
              "      <td>155.0000</td>\n",
              "      <td>155.00000</td>\n",
              "      <td>846.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>BMI</th>\n",
              "      <td>768.0</td>\n",
              "      <td>32.450911</td>\n",
              "      <td>6.875366</td>\n",
              "      <td>18.200</td>\n",
              "      <td>27.50000</td>\n",
              "      <td>32.0000</td>\n",
              "      <td>36.60000</td>\n",
              "      <td>67.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DiabetesPedigreeFunction</th>\n",
              "      <td>768.0</td>\n",
              "      <td>0.471876</td>\n",
              "      <td>0.331329</td>\n",
              "      <td>0.078</td>\n",
              "      <td>0.24375</td>\n",
              "      <td>0.3725</td>\n",
              "      <td>0.62625</td>\n",
              "      <td>2.42</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Age</th>\n",
              "      <td>768.0</td>\n",
              "      <td>33.240885</td>\n",
              "      <td>11.760232</td>\n",
              "      <td>21.000</td>\n",
              "      <td>24.00000</td>\n",
              "      <td>29.0000</td>\n",
              "      <td>41.00000</td>\n",
              "      <td>81.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Outcome</th>\n",
              "      <td>768.0</td>\n",
              "      <td>0.348958</td>\n",
              "      <td>0.476951</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.00000</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>1.00</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                          count        mean  ...        75%     max\n",
              "Pregnancies               768.0    3.845052  ...    6.00000   17.00\n",
              "Glucose                   768.0  121.682292  ...  140.25000  199.00\n",
              "BloodPressure             768.0   72.386719  ...   80.00000  122.00\n",
              "SkinThickness             768.0   29.108073  ...   32.00000   99.00\n",
              "Insulin                   768.0  155.281250  ...  155.00000  846.00\n",
              "BMI                       768.0   32.450911  ...   36.60000   67.10\n",
              "DiabetesPedigreeFunction  768.0    0.471876  ...    0.62625    2.42\n",
              "Age                       768.0   33.240885  ...   41.00000   81.00\n",
              "Outcome                   768.0    0.348958  ...    1.00000    1.00\n",
              "\n",
              "[9 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Dkq4nIcvxRdR"
      },
      "source": [
        "# Feature Scalling"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "suW7r46mxkGF"
      },
      "source": [
        "sc_X = StandardScaler()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RoFm8g64xqMR",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "073324ac-4ffe-4b1e-b8e2-ac21a98195ee"
      },
      "source": [
        "\n",
        "X_train = sc_X.fit_transform(X_train)\n",
        "print(X_train)\n",
        "X_test = sc_X.transform(X_test)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 0.90832902  0.93641795  0.44764174 ...  0.36863635  0.67740401\n",
            "   1.69955804]\n",
            " [ 0.03644676 -0.81630913 -1.05200558 ... -0.63294341 -0.07049698\n",
            "  -0.96569189]\n",
            " [-1.12606292  1.43247278  1.44740662 ...  2.81535261 -0.11855487\n",
            "  -0.88240283]\n",
            " ...\n",
            " [ 0.03644676 -0.91552009 -0.63543688 ... -1.13373329 -0.95656442\n",
            "  -1.04898095]\n",
            " [ 2.0708387  -1.21315299  0.11438678 ... -0.36108605 -0.50001442\n",
            "   0.11706589]\n",
            " [ 0.32707418  0.47343344  0.7808967  ... -0.08922869  0.52121586\n",
            "   2.94889395]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CNut0LoIWD4W",
        "outputId": "643eb768-6588-4890-8ad8-1acbba31c733"
      },
      "source": [
        "X_train.std(axis=0)\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1., 1., 1., 1., 1., 1., 1., 1.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SDtMvrVCx8vV",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "15f35b0f-1a10-4f61-d851-6d5800ec7081"
      },
      "source": [
        "import math\n",
        "math.sqrt(len(y_test))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "12.409673645990857"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XPzzczTnyGoU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b4b0da22-2d3e-4fbf-a8cb-2f4f1a4210f6"
      },
      "source": [
        "classifier = KNeighborsClassifier(n_neighbors = 11, p = 2, metric = 'euclidean')\n",
        "classifier.fit(X_train, y_train)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='euclidean',\n",
              "                     metric_params=None, n_jobs=None, n_neighbors=11, p=2,\n",
              "                     weights='uniform')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1cFjepPKyZYO",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0f10a24e-a37f-4147-fe22-ce2f7c10424a"
      },
      "source": [
        "y_pred = classifier.predict(X_test)\n",
        "y_pred"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0,\n",
              "       0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1,\n",
              "       1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1,\n",
              "       1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
              "       1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1,\n",
              "       0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
              "       0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "S6H90e97y9if"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YK1VBHuWzjF9"
      },
      "source": [
        "# Evaluation"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RqfWMvUhzlZQ"
      },
      "source": [
        "cm = confusion_matrix(y_test, y_pred)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QCzwIemKzrFf",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "5623d0d0-0864-4e55-f4c4-432f8caaaf1c"
      },
      "source": [
        "print(cm)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[94 13]\n",
            " [15 32]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SlVTQcUtztHf",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "45958152-5e08-4b2f-cd0f-8f0654d921b7"
      },
      "source": [
        "print(accuracy_score(y_test, y_pred))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.8181818181818182\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Y03-M6mzZeIe",
        "outputId": "d22b003d-3133-49c5-df0d-fa46a6eb1617"
      },
      "source": [
        "print(classification_report(y_test, y_pred))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.86      0.88      0.87       107\n",
            "           1       0.71      0.68      0.70        47\n",
            "\n",
            "    accuracy                           0.82       154\n",
            "   macro avg       0.79      0.78      0.78       154\n",
            "weighted avg       0.82      0.82      0.82       154\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "euA0cSBYz0qI",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "08ca7b42-17ae-43d9-b3f8-d6bf4d7c7673"
      },
      "source": [
        "X_test[1]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([-0.54480808, -0.48575468,  0.11279888,  0.08314323, -0.6501097 ,\n",
              "        0.13885774, -0.1876381 , -0.88240283])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bn7z3QrqSoha"
      },
      "source": [
        "def dib_pred(tp):\n",
        "  tp = sc_X.transform([tp])\n",
        "  pred = classifier.predict(tp)\n",
        "  print(pred)\n",
        "  if(pred == 0):\n",
        "    print('Positive')\n",
        "  else:\n",
        "    print('Negetive')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FU6uWZfxUOZp",
        "outputId": "427f103e-7574-4146-d463-b667436507fc"
      },
      "source": [
        "test = [1,\t85,\t66,\t29,\t0,\t26.6,\t0.351,\t31]\n",
        "dib_pred(test)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[0]\n",
            "Positive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "erEJx26KWN75",
        "outputId": "bd84ff5f-3553-42d0-99bf-d6e3d5a74192"
      },
      "source": [
        "\n",
        "sample = [0,\t137,\t40,\t35,\t168,\t43.1,\t2.288,\t33]\n",
        "dib_pred(sample)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1]\n",
            "Negetive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "i6qsFLLiij4A"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}