diff --git a/Extra/main.ipynb b/Extra/main.ipynb
index b53a95b..cd1c5bb 100644
--- a/Extra/main.ipynb
+++ b/Extra/main.ipynb
@@ -3464,7 +3464,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.8.11 ('base')",
+   "display_name": "Python 3.8.13 ('StrokePredictionModel')",
    "language": "python",
    "name": "python3"
   },
@@ -3483,7 +3483,7 @@
   "orig_nbformat": 4,
   "vscode": {
    "interpreter": {
-    "hash": "5819c1eaf6d552792a1bbc5e8998e6c2149ab26a1973a0d78107c0d9954e5ba0"
+    "hash": "6d6bab66b583e7661b89cead2220317a23c391a40fb8c52f2c1bcd3c04f3fbda"
    }
   }
  },
diff --git a/datasetCleaned.xlsx b/datasetCleaned.xlsx
new file mode 100644
index 0000000..86304b5
Binary files /dev/null and b/datasetCleaned.xlsx differ
diff --git a/main.ipynb b/main.ipynb
index 78035b3..97cc677 100644
--- a/main.ipynb
+++ b/main.ipynb
@@ -43,7 +43,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -74,7 +74,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -305,7 +305,7 @@
        "9       0  "
       ]
      },
-     "execution_count": 2,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -324,7 +324,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -359,7 +359,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -499,7 +499,7 @@
        "max           291.050000     97.600000      1.000000  "
       ]
      },
-     "execution_count": 4,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -510,7 +510,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -542,7 +542,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -683,7 +683,7 @@
        "4       0  "
       ]
      },
-     "execution_count": 6,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -696,7 +696,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -743,59 +743,59 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>39696</th>\n",
-       "      <td>24427</td>\n",
+       "      <th>25469</th>\n",
+       "      <td>40932</td>\n",
+       "      <td>1</td>\n",
+       "      <td>63.0</td>\n",
        "      <td>0</td>\n",
-       "      <td>20.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>73.20</td>\n",
+       "      <td>26.4</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
-       "      <td>91.23</td>\n",
-       "      <td>24.5</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "      <td>0</td>\n",
        "      <td>1</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9062</th>\n",
+       "      <td>23897</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4.0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
+       "      <td>86.33</td>\n",
+       "      <td>28.7</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
        "      <td>1</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>38440</th>\n",
-       "      <td>43933</td>\n",
-       "      <td>0</td>\n",
-       "      <td>57.0</td>\n",
+       "      <th>23973</th>\n",
+       "      <td>16201</td>\n",
+       "      <td>1</td>\n",
+       "      <td>48.0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>1</td>\n",
-       "      <td>59.41</td>\n",
-       "      <td>34.9</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>37515</th>\n",
-       "      <td>29824</td>\n",
-       "      <td>1</td>\n",
-       "      <td>34.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>104.07</td>\n",
-       "      <td>45.9</td>\n",
+       "      <td>80.87</td>\n",
+       "      <td>19.8</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
@@ -809,37 +809,40 @@
        "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>22940</th>\n",
-       "      <td>16030</td>\n",
+       "      <th>37135</th>\n",
+       "      <td>57514</td>\n",
        "      <td>1</td>\n",
-       "      <td>71.0</td>\n",
+       "      <td>55.0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>1</td>\n",
-       "      <td>96.03</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>132.16</td>\n",
+       "      <td>29.1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>1</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
-       "      <td>0</td>\n",
        "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
        "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>12098</th>\n",
-       "      <td>72294</td>\n",
-       "      <td>1</td>\n",
-       "      <td>59.0</td>\n",
+       "      <th>20314</th>\n",
+       "      <td>12476</td>\n",
+       "      <td>0</td>\n",
+       "      <td>62.0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>1</td>\n",
-       "      <td>90.06</td>\n",
-       "      <td>27.0</td>\n",
+       "      <td>110.97</td>\n",
+       "      <td>34.2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
        "      <td>0</td>\n",
@@ -848,9 +851,6 @@
        "      <td>0</td>\n",
        "      <td>1</td>\n",
        "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -858,49 +858,49 @@
       ],
       "text/plain": [
        "          id  gender   age  hypertension  heart_disease  ever_married  \\\n",
-       "39696  24427       0  20.0             0              0             0   \n",
-       "38440  43933       0  57.0             0              0             1   \n",
-       "37515  29824       1  34.0             0              0             1   \n",
-       "22940  16030       1  71.0             0              0             1   \n",
-       "12098  72294       1  59.0             0              0             1   \n",
+       "25469  40932       1  63.0             0              0             1   \n",
+       "9062   23897       1   4.0             0              0             0   \n",
+       "23973  16201       1  48.0             0              0             1   \n",
+       "37135  57514       1  55.0             0              0             1   \n",
+       "20314  12476       0  62.0             0              0             1   \n",
        "\n",
        "       avg_glucose_level   bmi  stroke  work_type_Govt_job  \\\n",
-       "39696              91.23  24.5       0                   1   \n",
-       "38440              59.41  34.9       0                   1   \n",
-       "37515             104.07  45.9       0                   0   \n",
-       "22940              96.03   NaN       0                   0   \n",
-       "12098              90.06  27.0       0                   0   \n",
+       "25469              73.20  26.4       0                   0   \n",
+       "9062               86.33  28.7       0                   0   \n",
+       "23973              80.87  19.8       0                   0   \n",
+       "37135             132.16  29.1       0                   1   \n",
+       "20314             110.97  34.2       0                   1   \n",
        "\n",
        "       work_type_Never_worked  work_type_Private  work_type_Self-employed  \\\n",
-       "39696                       0                  0                        0   \n",
-       "38440                       0                  0                        0   \n",
-       "37515                       0                  1                        0   \n",
-       "22940                       0                  1                        0   \n",
-       "12098                       0                  0                        1   \n",
+       "25469                       0                  0                        1   \n",
+       "9062                        0                  0                        0   \n",
+       "23973                       0                  1                        0   \n",
+       "37135                       0                  0                        0   \n",
+       "20314                       0                  0                        0   \n",
        "\n",
        "       work_type_children  Residence_type_Rural  Residence_type_Urban  \\\n",
-       "39696                   0                     0                     1   \n",
-       "38440                   0                     1                     0   \n",
-       "37515                   0                     0                     1   \n",
-       "22940                   0                     0                     1   \n",
-       "12098                   0                     1                     0   \n",
+       "25469                   0                     1                     0   \n",
+       "9062                    1                     0                     1   \n",
+       "23973                   0                     0                     1   \n",
+       "37135                   0                     1                     0   \n",
+       "20314                   0                     0                     1   \n",
        "\n",
        "       smoking_status_formerly smoked  smoking_status_never smoked  \\\n",
-       "39696                               0                            0   \n",
-       "38440                               1                            0   \n",
-       "37515                               0                            0   \n",
-       "22940                               1                            0   \n",
-       "12098                               0                            0   \n",
+       "25469                               0                            1   \n",
+       "9062                                0                            0   \n",
+       "23973                               0                            0   \n",
+       "37135                               0                            1   \n",
+       "20314                               0                            1   \n",
        "\n",
        "       smoking_status_smokes  \n",
-       "39696                      0  \n",
-       "38440                      0  \n",
-       "37515                      1  \n",
-       "22940                      0  \n",
-       "12098                      0  "
+       "25469                      0  \n",
+       "9062                       0  \n",
+       "23973                      1  \n",
+       "37135                      0  \n",
+       "20314                      0  "
       ]
      },
-     "execution_count": 7,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -912,7 +912,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -940,7 +940,7 @@
        "dtype: int64"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -951,13 +951,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
     "df = df.dropna(how = 'any', axis=0)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_excel('datasetCleaned.xlsx')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 10,
@@ -4981,7 +4990,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.9.13 ('BrainStrokePredictionMLEnv')",
+   "display_name": "Python 3.8.13 ('StrokePredictionModel')",
    "language": "python",
    "name": "python3"
   },
@@ -4995,12 +5004,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.13"
   },
   "orig_nbformat": 4,
   "vscode": {
    "interpreter": {
-    "hash": "54c59028773620d1ec7cf564885279046a3969c7da2b497982c8156e7da39d8c"
+    "hash": "6d6bab66b583e7661b89cead2220317a23c391a40fb8c52f2c1bcd3c04f3fbda"
    }
   }
  },
diff --git a/visualization_of_data.ipynb b/visualization_of_data.ipynb
new file mode 100644
index 0000000..610adc0
--- /dev/null
+++ b/visualization_of_data.ipynb
@@ -0,0 +1,620 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np \n",
+    "import pandas as pd \n",
+    "import os\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "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>id</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>age</th>\n",
+       "      <th>hypertension</th>\n",
+       "      <th>heart_disease</th>\n",
+       "      <th>ever_married</th>\n",
+       "      <th>work_type</th>\n",
+       "      <th>Residence_type</th>\n",
+       "      <th>avg_glucose_level</th>\n",
+       "      <th>bmi</th>\n",
+       "      <th>smoking_status</th>\n",
+       "      <th>stroke</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>30669</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>No</td>\n",
+       "      <td>children</td>\n",
+       "      <td>Rural</td>\n",
+       "      <td>95.12</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>30468</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>58.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Private</td>\n",
+       "      <td>Urban</td>\n",
+       "      <td>87.96</td>\n",
+       "      <td>39.2</td>\n",
+       "      <td>never smoked</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>16523</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Private</td>\n",
+       "      <td>Urban</td>\n",
+       "      <td>110.89</td>\n",
+       "      <td>17.6</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>56543</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>70.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Private</td>\n",
+       "      <td>Rural</td>\n",
+       "      <td>69.04</td>\n",
+       "      <td>35.9</td>\n",
+       "      <td>formerly smoked</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>46136</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>14.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Never_worked</td>\n",
+       "      <td>Rural</td>\n",
+       "      <td>161.28</td>\n",
+       "      <td>19.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>32257</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>47.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Private</td>\n",
+       "      <td>Urban</td>\n",
+       "      <td>210.95</td>\n",
+       "      <td>50.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>52800</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>52.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Private</td>\n",
+       "      <td>Urban</td>\n",
+       "      <td>77.59</td>\n",
+       "      <td>17.7</td>\n",
+       "      <td>formerly smoked</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>41413</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>75.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Self-employed</td>\n",
+       "      <td>Rural</td>\n",
+       "      <td>243.53</td>\n",
+       "      <td>27.0</td>\n",
+       "      <td>never smoked</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>15266</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>32.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Private</td>\n",
+       "      <td>Rural</td>\n",
+       "      <td>77.67</td>\n",
+       "      <td>32.3</td>\n",
+       "      <td>smokes</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>28674</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>74.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Self-employed</td>\n",
+       "      <td>Urban</td>\n",
+       "      <td>205.84</td>\n",
+       "      <td>54.6</td>\n",
+       "      <td>never smoked</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      id  gender   age  hypertension  heart_disease ever_married  \\\n",
+       "0  30669    Male   3.0             0              0           No   \n",
+       "1  30468    Male  58.0             1              0          Yes   \n",
+       "2  16523  Female   8.0             0              0           No   \n",
+       "3  56543  Female  70.0             0              0          Yes   \n",
+       "4  46136    Male  14.0             0              0           No   \n",
+       "5  32257  Female  47.0             0              0          Yes   \n",
+       "6  52800  Female  52.0             0              0          Yes   \n",
+       "7  41413  Female  75.0             0              1          Yes   \n",
+       "8  15266  Female  32.0             0              0          Yes   \n",
+       "9  28674  Female  74.0             1              0          Yes   \n",
+       "\n",
+       "       work_type Residence_type  avg_glucose_level   bmi   smoking_status  \\\n",
+       "0       children          Rural              95.12  18.0              NaN   \n",
+       "1        Private          Urban              87.96  39.2     never smoked   \n",
+       "2        Private          Urban             110.89  17.6              NaN   \n",
+       "3        Private          Rural              69.04  35.9  formerly smoked   \n",
+       "4   Never_worked          Rural             161.28  19.1              NaN   \n",
+       "5        Private          Urban             210.95  50.1              NaN   \n",
+       "6        Private          Urban              77.59  17.7  formerly smoked   \n",
+       "7  Self-employed          Rural             243.53  27.0     never smoked   \n",
+       "8        Private          Rural              77.67  32.3           smokes   \n",
+       "9  Self-employed          Urban             205.84  54.6     never smoked   \n",
+       "\n",
+       "   stroke  \n",
+       "0       0  \n",
+       "1       0  \n",
+       "2       0  \n",
+       "3       0  \n",
+       "4       0  \n",
+       "5       0  \n",
+       "6       0  \n",
+       "7       0  \n",
+       "8       0  \n",
+       "9       0  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('trainFile.csv')\n",
+    "df.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 43400 entries, 0 to 43399\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column             Non-Null Count  Dtype  \n",
+      "---  ------             --------------  -----  \n",
+      " 0   id                 43400 non-null  int64  \n",
+      " 1   gender             43400 non-null  object \n",
+      " 2   age                43400 non-null  float64\n",
+      " 3   hypertension       43400 non-null  int64  \n",
+      " 4   heart_disease      43400 non-null  int64  \n",
+      " 5   ever_married       43400 non-null  object \n",
+      " 6   work_type          43400 non-null  object \n",
+      " 7   Residence_type     43400 non-null  object \n",
+      " 8   avg_glucose_level  43400 non-null  float64\n",
+      " 9   bmi                41938 non-null  float64\n",
+      " 10  smoking_status     30108 non-null  object \n",
+      " 11  stroke             43400 non-null  int64  \n",
+      "dtypes: float64(3), int64(4), object(5)\n",
+      "memory usage: 4.0+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "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>id</th>\n",
+       "      <th>age</th>\n",
+       "      <th>hypertension</th>\n",
+       "      <th>heart_disease</th>\n",
+       "      <th>avg_glucose_level</th>\n",
+       "      <th>bmi</th>\n",
+       "      <th>stroke</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>43400.000000</td>\n",
+       "      <td>43400.000000</td>\n",
+       "      <td>43400.000000</td>\n",
+       "      <td>43400.000000</td>\n",
+       "      <td>43400.000000</td>\n",
+       "      <td>41938.000000</td>\n",
+       "      <td>43400.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>36326.142350</td>\n",
+       "      <td>42.217894</td>\n",
+       "      <td>0.093571</td>\n",
+       "      <td>0.047512</td>\n",
+       "      <td>104.482750</td>\n",
+       "      <td>28.605038</td>\n",
+       "      <td>0.018041</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>21072.134879</td>\n",
+       "      <td>22.519649</td>\n",
+       "      <td>0.291235</td>\n",
+       "      <td>0.212733</td>\n",
+       "      <td>43.111751</td>\n",
+       "      <td>7.770020</td>\n",
+       "      <td>0.133103</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.080000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>55.000000</td>\n",
+       "      <td>10.100000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>18038.500000</td>\n",
+       "      <td>24.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>77.540000</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>36351.500000</td>\n",
+       "      <td>44.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>91.580000</td>\n",
+       "      <td>27.700000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>54514.250000</td>\n",
+       "      <td>60.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>112.070000</td>\n",
+       "      <td>32.900000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>72943.000000</td>\n",
+       "      <td>82.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>291.050000</td>\n",
+       "      <td>97.600000</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 id           age  hypertension  heart_disease  \\\n",
+       "count  43400.000000  43400.000000  43400.000000   43400.000000   \n",
+       "mean   36326.142350     42.217894      0.093571       0.047512   \n",
+       "std    21072.134879     22.519649      0.291235       0.212733   \n",
+       "min        1.000000      0.080000      0.000000       0.000000   \n",
+       "25%    18038.500000     24.000000      0.000000       0.000000   \n",
+       "50%    36351.500000     44.000000      0.000000       0.000000   \n",
+       "75%    54514.250000     60.000000      0.000000       0.000000   \n",
+       "max    72943.000000     82.000000      1.000000       1.000000   \n",
+       "\n",
+       "       avg_glucose_level           bmi        stroke  \n",
+       "count       43400.000000  41938.000000  43400.000000  \n",
+       "mean          104.482750     28.605038      0.018041  \n",
+       "std            43.111751      7.770020      0.133103  \n",
+       "min            55.000000     10.100000      0.000000  \n",
+       "25%            77.540000     23.200000      0.000000  \n",
+       "50%            91.580000     27.700000      0.000000  \n",
+       "75%           112.070000     32.900000      0.000000  \n",
+       "max           291.050000     97.600000      1.000000  "
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['Male' 'Female' 'Other']\n",
+      "['children' 'Private' 'Never_worked' 'Self-employed' 'Govt_job']\n",
+      "['Rural' 'Urban']\n",
+      "[nan 'never smoked' 'formerly smoked' 'smokes']\n",
+      "['No' 'Yes']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df['gender'].unique())\n",
+    "print(df['work_type'].unique())\n",
+    "print(df['Residence_type'].unique())\n",
+    "print(df['smoking_status'].unique())\n",
+    "print(df['ever_married'].unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "id                       0\n",
+       "gender                   0\n",
+       "age                      0\n",
+       "hypertension             0\n",
+       "heart_disease            0\n",
+       "ever_married             0\n",
+       "work_type                0\n",
+       "Residence_type           0\n",
+       "avg_glucose_level        0\n",
+       "bmi                   1462\n",
+       "smoking_status       13292\n",
+       "stroke                   0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.dropna(how = 'any', axis=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 29072 entries, 1 to 43399\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column             Non-Null Count  Dtype  \n",
+      "---  ------             --------------  -----  \n",
+      " 0   id                 29072 non-null  int64  \n",
+      " 1   gender             29072 non-null  object \n",
+      " 2   age                29072 non-null  float64\n",
+      " 3   hypertension       29072 non-null  int64  \n",
+      " 4   heart_disease      29072 non-null  int64  \n",
+      " 5   ever_married       29072 non-null  object \n",
+      " 6   work_type          29072 non-null  object \n",
+      " 7   Residence_type     29072 non-null  object \n",
+      " 8   avg_glucose_level  29072 non-null  float64\n",
+      " 9   bmi                29072 non-null  float64\n",
+      " 10  smoking_status     29072 non-null  object \n",
+      " 11  stroke             29072 non-null  int64  \n",
+      "dtypes: float64(3), int64(4), object(5)\n",
+      "memory usage: 2.9+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_excel('datasetCleaned.xlsx')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "        <script type=\"text/javascript\">\n",
+       "        window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
+       "        if (window.MathJax && window.MathJax.Hub && window.MathJax.Hub.Config) {window.MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
+       "        if (typeof require !== 'undefined') {\n",
+       "        require.undef(\"plotly\");\n",
+       "        requirejs.config({\n",
+       "            paths: {\n",
+       "                'plotly': ['https://cdn.plot.ly/plotly-2.14.0.min']\n",
+       "            }\n",
+       "        });\n",
+       "        require(['plotly'], function(Plotly) {\n",
+       "            window._Plotly = Plotly;\n",
+       "        });\n",
+       "        }\n",
+       "        </script>\n",
+       "        "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import cufflinks as cf\n",
+    "\n",
+    "cf.go_offline()\n",
+    "cf.set_config_file(offline=False, world_readable=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.8.13 ('StrokePredictionModel')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.13"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "6d6bab66b583e7661b89cead2220317a23c391a40fb8c52f2c1bcd3c04f3fbda"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}