{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Multiple disease prediction system - diabetes.ipynb","provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyNUMtWtqiQOs+bSuSretvw5"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"markdown","metadata":{"id":"LnPbntVRnfvV"},"source":["Importing the Dependencies"]},{"cell_type":"code","metadata":{"id":"-71UtHzNVWjB","executionInfo":{"status":"ok","timestamp":1653200161038,"user_tz":-330,"elapsed":1362,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"source":["import numpy as np\n","import pandas as pd\n","from sklearn.model_selection import train_test_split\n","from sklearn import svm\n","from sklearn.metrics import accuracy_score"],"execution_count":1,"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","executionInfo":{"status":"ok","timestamp":1653200161039,"user_tz":-330,"elapsed":37,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"source":["# loading the diabetes dataset to a pandas DataFrame\n","diabetes_dataset = pd.read_csv('/content/diabetes.csv') "],"execution_count":2,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":206},"id":"-tjO09ncovoh","executionInfo":{"status":"ok","timestamp":1653200161040,"user_tz":-330,"elapsed":36,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"f4faaf8a-3fc8-413a-bbd4-bb272589a73c"},"source":["# printing the first 5 rows of the dataset\n","diabetes_dataset.head()"],"execution_count":3,"outputs":[{"output_type":"execute_result","data":{"text/plain":[" Pregnancies Glucose BloodPressure SkinThickness Insulin BMI \\\n","0 6 148 72 35 0 33.6 \n","1 1 85 66 29 0 26.6 \n","2 8 183 64 0 0 23.3 \n","3 1 89 66 23 94 28.1 \n","4 0 137 40 35 168 43.1 \n","\n"," DiabetesPedigreeFunction Age Outcome \n","0 0.627 50 1 \n","1 0.351 31 0 \n","2 0.672 32 1 \n","3 0.167 21 0 \n","4 2.288 33 1 "],"text/html":["\n"," <div id=\"df-543bb76d-9958-491b-8063-13990fcca102\">\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>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>\n"," <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-543bb76d-9958-491b-8063-13990fcca102')\"\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-543bb76d-9958-491b-8063-13990fcca102 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-543bb76d-9958-491b-8063-13990fcca102');\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":3}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"lynParo6pEMB","executionInfo":{"status":"ok","timestamp":1653200161040,"user_tz":-330,"elapsed":28,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"b8e97658-d5ae-4407-e3c0-f4b7b0d0321e"},"source":["# number of rows and Columns in this dataset\n","diabetes_dataset.shape"],"execution_count":4,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(768, 9)"]},"metadata":{},"execution_count":4}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":300},"id":"3NDJOlrEpmoL","executionInfo":{"status":"ok","timestamp":1653200161041,"user_tz":-330,"elapsed":26,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"1a166b9c-0ec1-42dc-e0f4-32924aa1ab65"},"source":["# getting the statistical measures of the data\n","diabetes_dataset.describe()"],"execution_count":5,"outputs":[{"output_type":"execute_result","data":{"text/plain":[" Pregnancies Glucose BloodPressure SkinThickness Insulin \\\n","count 768.000000 768.000000 768.000000 768.000000 768.000000 \n","mean 3.845052 120.894531 69.105469 20.536458 79.799479 \n","std 3.369578 31.972618 19.355807 15.952218 115.244002 \n","min 0.000000 0.000000 0.000000 0.000000 0.000000 \n","25% 1.000000 99.000000 62.000000 0.000000 0.000000 \n","50% 3.000000 117.000000 72.000000 23.000000 30.500000 \n","75% 6.000000 140.250000 80.000000 32.000000 127.250000 \n","max 17.000000 199.000000 122.000000 99.000000 846.000000 \n","\n"," BMI DiabetesPedigreeFunction Age Outcome \n","count 768.000000 768.000000 768.000000 768.000000 \n","mean 31.992578 0.471876 33.240885 0.348958 \n","std 7.884160 0.331329 11.760232 0.476951 \n","min 0.000000 0.078000 21.000000 0.000000 \n","25% 27.300000 0.243750 24.000000 0.000000 \n","50% 32.000000 0.372500 29.000000 0.000000 \n","75% 36.600000 0.626250 41.000000 1.000000 \n","max 67.100000 2.420000 81.000000 1.000000 "],"text/html":["\n"," <div id=\"df-e3ca105c-2704-4b75-87c3-2eac2e0e898f\">\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>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>\n"," <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e3ca105c-2704-4b75-87c3-2eac2e0e898f')\"\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-e3ca105c-2704-4b75-87c3-2eac2e0e898f 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-e3ca105c-2704-4b75-87c3-2eac2e0e898f');\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":5}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"LrpHzaGpp5dQ","executionInfo":{"status":"ok","timestamp":1653200161043,"user_tz":-330,"elapsed":27,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"5da75a35-5065-4c08-abb1-13bc921dec5a"},"source":["diabetes_dataset['Outcome'].value_counts()"],"execution_count":6,"outputs":[{"output_type":"execute_result","data":{"text/plain":["0 500\n","1 268\n","Name: Outcome, dtype: int64"]},"metadata":{},"execution_count":6}]},{"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":143},"id":"I6MWR0k_qSCK","executionInfo":{"status":"ok","timestamp":1653200161045,"user_tz":-330,"elapsed":27,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"1e817bc0-c41e-4181-a8e5-37885e765862"},"source":["diabetes_dataset.groupby('Outcome').mean()"],"execution_count":7,"outputs":[{"output_type":"execute_result","data":{"text/plain":[" Pregnancies Glucose BloodPressure SkinThickness Insulin \\\n","Outcome \n","0 3.298000 109.980000 68.184000 19.664000 68.792000 \n","1 4.865672 141.257463 70.824627 22.164179 100.335821 \n","\n"," BMI DiabetesPedigreeFunction Age \n","Outcome \n","0 30.304200 0.429734 31.190000 \n","1 35.142537 0.550500 37.067164 "],"text/html":["\n"," <div id=\"df-d6444b5f-72b8-4e7e-b7a2-6fc0efdc7816\">\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>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>\n"," <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d6444b5f-72b8-4e7e-b7a2-6fc0efdc7816')\"\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-d6444b5f-72b8-4e7e-b7a2-6fc0efdc7816 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-d6444b5f-72b8-4e7e-b7a2-6fc0efdc7816');\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","metadata":{"id":"RoDW7l9mqqHZ","executionInfo":{"status":"ok","timestamp":1653200161046,"user_tz":-330,"elapsed":27,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"source":["# separating the data and labels\n","X = diabetes_dataset.drop(columns = 'Outcome', axis=1)\n","Y = diabetes_dataset['Outcome']"],"execution_count":8,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"3eiRW9M9raMm","executionInfo":{"status":"ok","timestamp":1653200161046,"user_tz":-330,"elapsed":26,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"107aefe8-a40e-4a8c-efa4-e6a4929b8343"},"source":["print(X)"],"execution_count":9,"outputs":[{"output_type":"stream","name":"stdout","text":[" Pregnancies Glucose BloodPressure SkinThickness Insulin BMI \\\n","0 6 148 72 35 0 33.6 \n","1 1 85 66 29 0 26.6 \n","2 8 183 64 0 0 23.3 \n","3 1 89 66 23 94 28.1 \n","4 0 137 40 35 168 43.1 \n",".. ... ... ... ... ... ... \n","763 10 101 76 48 180 32.9 \n","764 2 122 70 27 0 36.8 \n","765 5 121 72 23 112 26.2 \n","766 1 126 60 0 0 30.1 \n","767 1 93 70 31 0 30.4 \n","\n"," DiabetesPedigreeFunction Age \n","0 0.627 50 \n","1 0.351 31 \n","2 0.672 32 \n","3 0.167 21 \n","4 2.288 33 \n",".. ... ... \n","763 0.171 63 \n","764 0.340 27 \n","765 0.245 30 \n","766 0.349 47 \n","767 0.315 23 \n","\n","[768 rows x 8 columns]\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"AoxgTJAMrcCl","executionInfo":{"status":"ok","timestamp":1653200161047,"user_tz":-330,"elapsed":25,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"afb40f51-fd9c-43ff-c51f-7b49a7f9b152"},"source":["print(Y)"],"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","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"]}]},{"cell_type":"markdown","metadata":{"id":"gHciEFkxsoQP"},"source":["Train Test Split"]},{"cell_type":"code","metadata":{"id":"AEfKGj_yslvD","executionInfo":{"status":"ok","timestamp":1653200161047,"user_tz":-330,"elapsed":21,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"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":11,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"DR05T-o0t3FQ","executionInfo":{"status":"ok","timestamp":1653200161048,"user_tz":-330,"elapsed":21,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"1e35e84b-b1ac-4cf3-c2af-31eb3bf2e71c"},"source":["print(X.shape, X_train.shape, X_test.shape)"],"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["(768, 8) (614, 8) (154, 8)\n"]}]},{"cell_type":"markdown","metadata":{"id":"ElJ3tkOtuC_n"},"source":["Training the Model"]},{"cell_type":"code","metadata":{"id":"5szLWHlNt9xc","executionInfo":{"status":"ok","timestamp":1653200161048,"user_tz":-330,"elapsed":19,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"source":["classifier = svm.SVC(kernel='linear')"],"execution_count":13,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ncJWY_7suPAb","executionInfo":{"status":"ok","timestamp":1653200163540,"user_tz":-330,"elapsed":2510,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"00260e64-02fd-426f-d274-717bbf9318d6"},"source":["#training the support vector Machine Classifier\n","classifier.fit(X_train, Y_train)"],"execution_count":14,"outputs":[{"output_type":"execute_result","data":{"text/plain":["SVC(kernel='linear')"]},"metadata":{},"execution_count":14}]},{"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","executionInfo":{"status":"ok","timestamp":1653200163541,"user_tz":-330,"elapsed":27,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"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":15,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"mmJ22qhVvNwj","executionInfo":{"status":"ok","timestamp":1653200163541,"user_tz":-330,"elapsed":25,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"ec01e94f-dbed-4286-9413-a05dab7eb7bc"},"source":["print('Accuracy score of the training data : ', training_data_accuracy)"],"execution_count":16,"outputs":[{"output_type":"stream","name":"stdout","text":["Accuracy score of the training data : 0.7833876221498371\n"]}]},{"cell_type":"code","metadata":{"id":"G2CICFMEvcCl","executionInfo":{"status":"ok","timestamp":1653200163542,"user_tz":-330,"elapsed":24,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"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":17,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"i2GcW_t_vz7C","executionInfo":{"status":"ok","timestamp":1653200163542,"user_tz":-330,"elapsed":23,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"638e2f46-36ec-471a-b9f7-ac7e319e5fea"},"source":["print('Accuracy score of the test data : ', test_data_accuracy)"],"execution_count":18,"outputs":[{"output_type":"stream","name":"stdout","text":["Accuracy score of the test data : 0.7727272727272727\n"]}]},{"cell_type":"markdown","metadata":{"id":"gq8ZX1xpwPF5"},"source":["Making a Predictive System"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"U-ULRe4yv5tH","executionInfo":{"status":"ok","timestamp":1653200163543,"user_tz":-330,"elapsed":21,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"6d829789-0c86-469d-ec6a-f20276f0a3ed"},"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","prediction = classifier.predict(input_data_reshaped)\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":19,"outputs":[{"output_type":"stream","name":"stdout","text":["[1]\n","The person is diabetic\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.7/dist-packages/sklearn/base.py:451: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n"," \"X does not have valid feature names, but\"\n"]}]},{"cell_type":"markdown","metadata":{"id":"FCHCMHpshHU4"},"source":["Saving the trained model"]},{"cell_type":"code","metadata":{"id":"cdmTOR4MhHCB","executionInfo":{"status":"ok","timestamp":1653200163543,"user_tz":-330,"elapsed":18,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"source":["import pickle"],"execution_count":20,"outputs":[]},{"cell_type":"code","metadata":{"id":"4gN09lokhKuZ","executionInfo":{"status":"ok","timestamp":1653200163543,"user_tz":-330,"elapsed":17,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"source":["filename = 'diabetes_model.sav'\n","pickle.dump(classifier, open(filename, 'wb'))"],"execution_count":21,"outputs":[]},{"cell_type":"code","metadata":{"id":"IKW4D5CqhP5X","executionInfo":{"status":"ok","timestamp":1653200163544,"user_tz":-330,"elapsed":18,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}}},"source":["# loading the saved model\n","loaded_model = pickle.load(open('diabetes_model.sav', 'rb'))"],"execution_count":22,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"exbg9-VWiHRx","executionInfo":{"status":"ok","timestamp":1653200163544,"user_tz":-330,"elapsed":17,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"e9d0e88b-67b8-457a-a252-22633cdc382e"},"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","prediction = loaded_model.predict(input_data_reshaped)\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":23,"outputs":[{"output_type":"stream","name":"stdout","text":["[1]\n","The person is diabetic\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.7/dist-packages/sklearn/base.py:451: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n"," \"X does not have valid feature names, but\"\n"]}]},{"cell_type":"code","source":["for column in X.columns:\n"," print(column)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"IP-TYuEFOTF4","executionInfo":{"status":"ok","timestamp":1653200163545,"user_tz":-330,"elapsed":15,"user":{"displayName":"siddhardh selvam","userId":"13966379820454708749"}},"outputId":"508fa3ac-ee67-4361-e558-d6b22b9c2c2c"},"execution_count":24,"outputs":[{"output_type":"stream","name":"stdout","text":["Pregnancies\n","Glucose\n","BloodPressure\n","SkinThickness\n","Insulin\n","BMI\n","DiabetesPedigreeFunction\n","Age\n"]}]}]}