Diabetes_Prediction.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LnPbntVRnfvV"
      },
      "source": [
        "Importing the Dependencies"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-71UtHzNVWjB"
      },
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn import svm\n",
        "from sklearn.metrics import accuracy_score"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bmfOfG8joBBy"
      },
      "source": [
        "Data Collection and Analysis\n",
        "\n",
        "PIMA Diabetes Dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Xpw6Mj_pn_TL"
      },
      "source": [
        "# loading the diabetes dataset to a pandas DataFrame\n",
        "diabetes_dataset = pd.read_csv('diabetes.csv') "
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eupSUC7yoo9M"
      },
      "source": [
        "pd.read_csv?"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 198
        },
        "id": "-tjO09ncovoh",
        "outputId": "c566e83c-4729-4e62-887d-485b52b923d9"
      },
      "source": [
        "# printing the first 5 rows of the dataset\n",
        "diabetes_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": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lynParo6pEMB",
        "outputId": "4c71bc91-33d7-45a8-8510-db04a31fa634"
      },
      "source": [
        "# number of rows and Columns in this dataset\n",
        "diabetes_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": 288
        },
        "id": "3NDJOlrEpmoL",
        "outputId": "afa1fd6c-4c87-4f2a-d91f-ef7c775701e5"
      },
      "source": [
        "# getting the statistical measures of the data\n",
        "diabetes_dataset.describe()"
      ],
      "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>count</th>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>3.845052</td>\n",
              "      <td>120.894531</td>\n",
              "      <td>69.105469</td>\n",
              "      <td>20.536458</td>\n",
              "      <td>79.799479</td>\n",
              "      <td>31.992578</td>\n",
              "      <td>0.471876</td>\n",
              "      <td>33.240885</td>\n",
              "      <td>0.348958</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>3.369578</td>\n",
              "      <td>31.972618</td>\n",
              "      <td>19.355807</td>\n",
              "      <td>15.952218</td>\n",
              "      <td>115.244002</td>\n",
              "      <td>7.884160</td>\n",
              "      <td>0.331329</td>\n",
              "      <td>11.760232</td>\n",
              "      <td>0.476951</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.078000</td>\n",
              "      <td>21.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>99.000000</td>\n",
              "      <td>62.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>27.300000</td>\n",
              "      <td>0.243750</td>\n",
              "      <td>24.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>3.000000</td>\n",
              "      <td>117.000000</td>\n",
              "      <td>72.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>30.500000</td>\n",
              "      <td>32.000000</td>\n",
              "      <td>0.372500</td>\n",
              "      <td>29.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>6.000000</td>\n",
              "      <td>140.250000</td>\n",
              "      <td>80.000000</td>\n",
              "      <td>32.000000</td>\n",
              "      <td>127.250000</td>\n",
              "      <td>36.600000</td>\n",
              "      <td>0.626250</td>\n",
              "      <td>41.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>17.000000</td>\n",
              "      <td>199.000000</td>\n",
              "      <td>122.000000</td>\n",
              "      <td>99.000000</td>\n",
              "      <td>846.000000</td>\n",
              "      <td>67.100000</td>\n",
              "      <td>2.420000</td>\n",
              "      <td>81.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       Pregnancies     Glucose  ...         Age     Outcome\n",
              "count   768.000000  768.000000  ...  768.000000  768.000000\n",
              "mean      3.845052  120.894531  ...   33.240885    0.348958\n",
              "std       3.369578   31.972618  ...   11.760232    0.476951\n",
              "min       0.000000    0.000000  ...   21.000000    0.000000\n",
              "25%       1.000000   99.000000  ...   24.000000    0.000000\n",
              "50%       3.000000  117.000000  ...   29.000000    0.000000\n",
              "75%       6.000000  140.250000  ...   41.000000    1.000000\n",
              "max      17.000000  199.000000  ...   81.000000    1.000000\n",
              "\n",
              "[8 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LrpHzaGpp5dQ",
        "outputId": "b265441f-7d9f-4f4d-9128-7b80fa4e41c9"
      },
      "source": [
        "diabetes_dataset['Outcome'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    500\n",
              "1    268\n",
              "Name: Outcome, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cB1qRaNcqeh5"
      },
      "source": [
        "0 --> Non-Diabetic\n",
        "\n",
        "1 --> Diabetic"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 138
        },
        "id": "I6MWR0k_qSCK",
        "outputId": "d2aba08b-5d59-470d-d48b-da3c7befcc38"
      },
      "source": [
        "diabetes_dataset.groupby('Outcome').mean()"
      ],
      "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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Outcome</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>3.298000</td>\n",
              "      <td>109.980000</td>\n",
              "      <td>68.184000</td>\n",
              "      <td>19.664000</td>\n",
              "      <td>68.792000</td>\n",
              "      <td>30.304200</td>\n",
              "      <td>0.429734</td>\n",
              "      <td>31.190000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>4.865672</td>\n",
              "      <td>141.257463</td>\n",
              "      <td>70.824627</td>\n",
              "      <td>22.164179</td>\n",
              "      <td>100.335821</td>\n",
              "      <td>35.142537</td>\n",
              "      <td>0.550500</td>\n",
              "      <td>37.067164</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "         Pregnancies     Glucose  ...  DiabetesPedigreeFunction        Age\n",
              "Outcome                           ...                                     \n",
              "0           3.298000  109.980000  ...                  0.429734  31.190000\n",
              "1           4.865672  141.257463  ...                  0.550500  37.067164\n",
              "\n",
              "[2 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RoDW7l9mqqHZ"
      },
      "source": [
        "# separating the data and labels\n",
        "X = diabetes_dataset.drop(columns = 'Outcome', axis=1)\n",
        "Y = diabetes_dataset['Outcome']"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3eiRW9M9raMm",
        "outputId": "0484d0a6-eefd-4964-f3f1-062b48147705"
      },
      "source": [
        "print(X)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "     Pregnancies  Glucose  BloodPressure  ...   BMI  DiabetesPedigreeFunction  Age\n",
            "0              6      148             72  ...  33.6                     0.627   50\n",
            "1              1       85             66  ...  26.6                     0.351   31\n",
            "2              8      183             64  ...  23.3                     0.672   32\n",
            "3              1       89             66  ...  28.1                     0.167   21\n",
            "4              0      137             40  ...  43.1                     2.288   33\n",
            "..           ...      ...            ...  ...   ...                       ...  ...\n",
            "763           10      101             76  ...  32.9                     0.171   63\n",
            "764            2      122             70  ...  36.8                     0.340   27\n",
            "765            5      121             72  ...  26.2                     0.245   30\n",
            "766            1      126             60  ...  30.1                     0.349   47\n",
            "767            1       93             70  ...  30.4                     0.315   23\n",
            "\n",
            "[768 rows x 8 columns]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AoxgTJAMrcCl",
        "outputId": "1b30c829-67e6-4e0f-c930-4dc054a3139d"
      },
      "source": [
        "print(Y)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0      1\n",
            "1      0\n",
            "2      1\n",
            "3      0\n",
            "4      1\n",
            "      ..\n",
            "763    0\n",
            "764    0\n",
            "765    0\n",
            "766    1\n",
            "767    0\n",
            "Name: Outcome, Length: 768, dtype: int64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "umAbo_kqrlzI"
      },
      "source": [
        "Data Standardization"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "njfM5X60rgnc"
      },
      "source": [
        "scaler = StandardScaler()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "g0ai5ARbr53p",
        "outputId": "f2c6f6f7-87c8-4468-cbd5-e0b6b8636d60"
      },
      "source": [
        "scaler.fit(X)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "StandardScaler(copy=True, with_mean=True, with_std=True)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FHxNwPuZr-kD"
      },
      "source": [
        "standardized_data = scaler.transform(X)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fjMwZ5x6sPUJ",
        "outputId": "2d8295c4-c5d0-4922-ba45-59d4ec114d36"
      },
      "source": [
        "print(standardized_data)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 0.63994726  0.84832379  0.14964075 ...  0.20401277  0.46849198\n",
            "   1.4259954 ]\n",
            " [-0.84488505 -1.12339636 -0.16054575 ... -0.68442195 -0.36506078\n",
            "  -0.19067191]\n",
            " [ 1.23388019  1.94372388 -0.26394125 ... -1.10325546  0.60439732\n",
            "  -0.10558415]\n",
            " ...\n",
            " [ 0.3429808   0.00330087  0.14964075 ... -0.73518964 -0.68519336\n",
            "  -0.27575966]\n",
            " [-0.84488505  0.1597866  -0.47073225 ... -0.24020459 -0.37110101\n",
            "   1.17073215]\n",
            " [-0.84488505 -0.8730192   0.04624525 ... -0.20212881 -0.47378505\n",
            "  -0.87137393]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZxWSl4SGsRjE"
      },
      "source": [
        "X = standardized_data\n",
        "Y = diabetes_dataset['Outcome']"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lhJF_7QjsjmP",
        "outputId": "56cb64d4-a50b-4ecc-fcae-64df4dd293e7"
      },
      "source": [
        "print(X)\n",
        "print(Y)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 0.63994726  0.84832379  0.14964075 ...  0.20401277  0.46849198\n",
            "   1.4259954 ]\n",
            " [-0.84488505 -1.12339636 -0.16054575 ... -0.68442195 -0.36506078\n",
            "  -0.19067191]\n",
            " [ 1.23388019  1.94372388 -0.26394125 ... -1.10325546  0.60439732\n",
            "  -0.10558415]\n",
            " ...\n",
            " [ 0.3429808   0.00330087  0.14964075 ... -0.73518964 -0.68519336\n",
            "  -0.27575966]\n",
            " [-0.84488505  0.1597866  -0.47073225 ... -0.24020459 -0.37110101\n",
            "   1.17073215]\n",
            " [-0.84488505 -0.8730192   0.04624525 ... -0.20212881 -0.47378505\n",
            "  -0.87137393]]\n",
            "0      1\n",
            "1      0\n",
            "2      1\n",
            "3      0\n",
            "4      1\n",
            "      ..\n",
            "763    0\n",
            "764    0\n",
            "765    0\n",
            "766    1\n",
            "767    0\n",
            "Name: Outcome, Length: 768, dtype: int64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gHciEFkxsoQP"
      },
      "source": [
        "Train Test Split"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AEfKGj_yslvD"
      },
      "source": [
        "X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size = 0.2, stratify=Y, random_state=2)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DR05T-o0t3FQ",
        "outputId": "fe062ec2-78bc-4fdf-a49e-ff5f8f41dab8"
      },
      "source": [
        "print(X.shape, X_train.shape, X_test.shape)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "(768, 8) (614, 8) (154, 8)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ElJ3tkOtuC_n"
      },
      "source": [
        "Training the Model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5szLWHlNt9xc"
      },
      "source": [
        "classifier = svm.SVC(kernel='linear')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ncJWY_7suPAb",
        "outputId": "79051336-314b-4bb8-8ecc-0042130e3b62"
      },
      "source": [
        "#training the support vector Machine Classifier\n",
        "classifier.fit(X_train, Y_train)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "SVC(C=1.0, break_ties=False, cache_size=200, class_weight=None, coef0=0.0,\n",
              "    decision_function_shape='ovr', degree=3, gamma='scale', kernel='linear',\n",
              "    max_iter=-1, probability=False, random_state=None, shrinking=True,\n",
              "    tol=0.001, verbose=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UV4-CAfquiyP"
      },
      "source": [
        "Model Evaluation"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yhAjGPJWunXa"
      },
      "source": [
        "Accuracy Score"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fJLEPQK7ueXp"
      },
      "source": [
        "# accuracy score on the training data\n",
        "X_train_prediction = classifier.predict(X_train)\n",
        "training_data_accuracy = accuracy_score(X_train_prediction, Y_train)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mmJ22qhVvNwj",
        "outputId": "7a88a78f-6bde-4fc7-c0ab-8202fb64666d"
      },
      "source": [
        "print('Accuracy score of the training data : ', training_data_accuracy)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy score of the training data :  0.7866449511400652\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "G2CICFMEvcCl"
      },
      "source": [
        "# accuracy score on the test data\n",
        "X_test_prediction = classifier.predict(X_test)\n",
        "test_data_accuracy = accuracy_score(X_test_prediction, Y_test)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "i2GcW_t_vz7C",
        "outputId": "40615c34-c1c7-4740-df59-6f3ae56385d7"
      },
      "source": [
        "print('Accuracy score of the test data : ', test_data_accuracy)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy score of the test data :  0.7727272727272727\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gq8ZX1xpwPF5"
      },
      "source": [
        "Making a Predictive System"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "U-ULRe4yv5tH",
        "outputId": "98388b32-53bc-4c51-a04b-ca80a016f8bf"
      },
      "source": [
        "input_data = (5,166,72,19,175,25.8,0.587,51)\n",
        "\n",
        "# changing the input_data to numpy array\n",
        "input_data_as_numpy_array = np.asarray(input_data)\n",
        "\n",
        "# reshape the array as we are predicting for one instance\n",
        "input_data_reshaped = input_data_as_numpy_array.reshape(1,-1)\n",
        "\n",
        "# standardize the input data\n",
        "std_data = scaler.transform(input_data_reshaped)\n",
        "print(std_data)\n",
        "\n",
        "prediction = classifier.predict(std_data)\n",
        "print(prediction)\n",
        "\n",
        "if (prediction[0] == 0):\n",
        "  print('The person is not diabetic')\n",
        "else:\n",
        "  print('The person is diabetic')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 0.3429808   1.41167241  0.14964075 -0.09637905  0.82661621 -0.78595734\n",
            "   0.34768723  1.51108316]]\n",
            "[1]\n",
            "The person is diabetic\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ex2A_pr4yCpm"
      },
      "source": [],
      "execution_count": null,
      "outputs": []
    }
  ]
}