{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "20c63983",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T21:17:51.007242Z",
     "iopub.status.busy": "2023-02-14T21:17:51.006125Z",
     "iopub.status.idle": "2023-02-14T21:17:51.034704Z",
     "shell.execute_reply": "2023-02-14T21:17:51.033652Z",
     "shell.execute_reply.started": "2023-02-14T21:17:51.007133Z"
    },
    "papermill": {
     "duration": 0.017114,
     "end_time": "2023-02-14T22:16:24.204070",
     "exception": false,
     "start_time": "2023-02-14T22:16:24.186956",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Title**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "656dd47b",
   "metadata": {
    "papermill": {
     "duration": 0.014801,
     "end_time": "2023-02-14T22:16:24.233905",
     "exception": false,
     "start_time": "2023-02-14T22:16:24.219104",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## **Perfect Diabetes melitus Predicting with 3 Machine learning models**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e927a3f3",
   "metadata": {
    "papermill": {
     "duration": 0.015616,
     "end_time": "2023-02-14T22:16:24.265132",
     "exception": false,
     "start_time": "2023-02-14T22:16:24.249516",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Import libraries**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2e0d1a3e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:24.298224Z",
     "iopub.status.busy": "2023-02-14T22:16:24.297576Z",
     "iopub.status.idle": "2023-02-14T22:16:25.773976Z",
     "shell.execute_reply": "2023-02-14T22:16:25.772740Z"
    },
    "papermill": {
     "duration": 1.496603,
     "end_time": "2023-02-14T22:16:25.777137",
     "exception": false,
     "start_time": "2023-02-14T22:16:24.280534",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "done importing\n"
     ]
    }
   ],
   "source": [
    "# Import libraries\n",
    "\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "import seaborn as sns\n",
    "from scipy import stats\n",
    "\n",
    "from sklearn.feature_selection import SelectKBest\n",
    "from sklearn.feature_selection import chi2\n",
    "from sklearn.preprocessing import QuantileTransformer\n",
    "from sklearn.preprocessing import StandardScaler,MinMaxScaler\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from mlxtend.plotting import plot_confusion_matrix\n",
    "from sklearn.linear_model import LogisticRegressionCV\n",
    "\n",
    "from sklearn.ensemble import ExtraTreesClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "\n",
    "from sklearn.utils import shuffle\n",
    "from sklearn.svm import SVC, LinearSVC\n",
    "from sklearn.ensemble import VotingClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score , classification_report,ConfusionMatrixDisplay,precision_score,recall_score, f1_score,roc_auc_score,roc_curve, balanced_accuracy_score\n",
    "\n",
    "from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS\n",
    "print('done importing')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2383fbc1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:25.811454Z",
     "iopub.status.busy": "2023-02-14T22:16:25.811036Z",
     "iopub.status.idle": "2023-02-14T22:16:26.090420Z",
     "shell.execute_reply": "2023-02-14T22:16:26.089049Z"
    },
    "papermill": {
     "duration": 0.298589,
     "end_time": "2023-02-14T22:16:26.092936",
     "exception": false,
     "start_time": "2023-02-14T22:16:25.794347",
     "status": "completed"
    },
    "tags": []
   },
   "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>Age</th>\n",
       "      <th>Sex</th>\n",
       "      <th>HighChol</th>\n",
       "      <th>CholCheck</th>\n",
       "      <th>BMI</th>\n",
       "      <th>Smoker</th>\n",
       "      <th>HeartDiseaseorAttack</th>\n",
       "      <th>PhysActivity</th>\n",
       "      <th>Fruits</th>\n",
       "      <th>Veggies</th>\n",
       "      <th>HvyAlcoholConsump</th>\n",
       "      <th>GenHlth</th>\n",
       "      <th>MentHlth</th>\n",
       "      <th>PhysHlth</th>\n",
       "      <th>DiffWalk</th>\n",
       "      <th>Stroke</th>\n",
       "      <th>HighBP</th>\n",
       "      <th>Diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>13.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Age  Sex  HighChol  CholCheck   BMI  Smoker  HeartDiseaseorAttack  \\\n",
       "0   4.0  1.0       0.0        1.0  26.0     0.0                   0.0   \n",
       "1  12.0  1.0       1.0        1.0  26.0     1.0                   0.0   \n",
       "2  13.0  1.0       0.0        1.0  26.0     0.0                   0.0   \n",
       "3  11.0  1.0       1.0        1.0  28.0     1.0                   0.0   \n",
       "4   8.0  0.0       0.0        1.0  29.0     1.0                   0.0   \n",
       "\n",
       "   PhysActivity  Fruits  Veggies  HvyAlcoholConsump  GenHlth  MentHlth  \\\n",
       "0           1.0     0.0      1.0                0.0      3.0       5.0   \n",
       "1           0.0     1.0      0.0                0.0      3.0       0.0   \n",
       "2           1.0     1.0      1.0                0.0      1.0       0.0   \n",
       "3           1.0     1.0      1.0                0.0      3.0       0.0   \n",
       "4           1.0     1.0      1.0                0.0      2.0       0.0   \n",
       "\n",
       "   PhysHlth  DiffWalk  Stroke  HighBP  Diabetes  \n",
       "0      30.0       0.0     0.0     1.0       0.0  \n",
       "1       0.0       0.0     1.0     1.0       0.0  \n",
       "2      10.0       0.0     0.0     0.0       0.0  \n",
       "3       3.0       0.0     0.0     1.0       0.0  \n",
       "4       0.0       0.0     0.0     0.0       0.0  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm_raw = pd.read_csv(\"/kaggle/input/health-dataset/diabetes_data.csv\")\n",
    "dm_raw.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "84248688",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T21:20:49.272837Z",
     "iopub.status.busy": "2023-02-14T21:20:49.272356Z",
     "iopub.status.idle": "2023-02-14T21:20:49.287950Z",
     "shell.execute_reply": "2023-02-14T21:20:49.285641Z",
     "shell.execute_reply.started": "2023-02-14T21:20:49.272798Z"
    },
    "papermill": {
     "duration": 0.017118,
     "end_time": "2023-02-14T22:16:26.127837",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.110719",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**Describe columns**\n",
    "\n",
    "Age: 13-level age category (_AGEG5YR see codebook)\n",
    "\n",
    "1 = 18-24 / 2 = 25-29 / 3 = 30-34 / 4 = 35-39 / 5 = 40-44 / 6 = 45-49 / 7 = 50-54 / 8 = 55-59 / 9 = 60-64 / 10 = 65-69 / 11 = 70-74 / 12 = 75-79 / 13 = 80 or older\n",
    "\n",
    "Sex: patient's gender (1: male; 0: female)\n",
    "\n",
    "HighChol: 0 = no high cholesterol 1 = high cholesterol\n",
    "\n",
    "CholCheck: 0 = no cholesterol check in 5 years 1 = yes cholesterol check in 5 years\n",
    "\n",
    "BMI: Body Mass Index\n",
    "\n",
    "Smoker: Have you smoked at least 100 cigarettes in your entire life? [Note: 5 packs = 100 cigarettes] 0 = no 1 = yes\n",
    "\n",
    "HeartDiseaseorAttack: coronary heart disease (CHD) or myocardial infarction (MI) 0 = no 1 = yes\n",
    "\n",
    "PhysActivity: physical activity in past 30 days - not including job 0 = no 1 = yes\n",
    "\n",
    "Fruits: Consume Fruit 1 or more times per day 0 = no 1 = yes\n",
    "\n",
    "Veggies: Consume Vegetables 1 or more times per day 0 = no 1 = yes\n",
    "\n",
    "HvyAlcoholConsump: (adult men >=14 drinks per week and adult women>=7 drinks per week) 0 = no 1 = yes\n",
    "\n",
    "GenHlth: Would you say that in general your health is: scale 1-5 1 = excellent 2 = very good 3 = good 4 = fair 5 = poor\n",
    "\n",
    "MentHlth: days of poor mental health scale 1-30 days\n",
    "\n",
    "PhysHlth: physical illness or injury days in past 30 days scale 1-30\n",
    "\n",
    "DiffWalk: Do you have serious difficulty walking or climbing stairs? 0 = no 1 = yes\n",
    "\n",
    "Stroke: you ever had a stroke. 0 = no, 1 = yes\n",
    "\n",
    "HighBP: 0 = no high, BP 1 = high BP\n",
    "\n",
    "Diabetes: 0 = no diabetes, 1 = diabetes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "57d62cfc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:26.166148Z",
     "iopub.status.busy": "2023-02-14T22:16:26.165707Z",
     "iopub.status.idle": "2023-02-14T22:16:26.196127Z",
     "shell.execute_reply": "2023-02-14T22:16:26.195153Z"
    },
    "papermill": {
     "duration": 0.052756,
     "end_time": "2023-02-14T22:16:26.200849",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.148093",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 70692 entries, 0 to 70691\n",
      "Data columns (total 18 columns):\n",
      " #   Column                Non-Null Count  Dtype  \n",
      "---  ------                --------------  -----  \n",
      " 0   Age                   70692 non-null  float64\n",
      " 1   Sex                   70692 non-null  float64\n",
      " 2   HighChol              70692 non-null  float64\n",
      " 3   CholCheck             70692 non-null  float64\n",
      " 4   BMI                   70692 non-null  float64\n",
      " 5   Smoker                70692 non-null  float64\n",
      " 6   HeartDiseaseorAttack  70692 non-null  float64\n",
      " 7   PhysActivity          70692 non-null  float64\n",
      " 8   Fruits                70692 non-null  float64\n",
      " 9   Veggies               70692 non-null  float64\n",
      " 10  HvyAlcoholConsump     70692 non-null  float64\n",
      " 11  GenHlth               70692 non-null  float64\n",
      " 12  MentHlth              70692 non-null  float64\n",
      " 13  PhysHlth              70692 non-null  float64\n",
      " 14  DiffWalk              70692 non-null  float64\n",
      " 15  Stroke                70692 non-null  float64\n",
      " 16  HighBP                70692 non-null  float64\n",
      " 17  Diabetes              70692 non-null  float64\n",
      "dtypes: float64(18)\n",
      "memory usage: 9.7 MB\n"
     ]
    }
   ],
   "source": [
    "#get column names\n",
    "dm_raw.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "12e84400",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:26.238230Z",
     "iopub.status.busy": "2023-02-14T22:16:26.237479Z",
     "iopub.status.idle": "2023-02-14T22:16:26.242903Z",
     "shell.execute_reply": "2023-02-14T22:16:26.241819Z"
    },
    "papermill": {
     "duration": 0.026733,
     "end_time": "2023-02-14T22:16:26.245358",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.218625",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#No null variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "f285013c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:26.280420Z",
     "iopub.status.busy": "2023-02-14T22:16:26.279660Z",
     "iopub.status.idle": "2023-02-14T22:16:26.313593Z",
     "shell.execute_reply": "2023-02-14T22:16:26.312625Z"
    },
    "papermill": {
     "duration": 0.05424,
     "end_time": "2023-02-14T22:16:26.316187",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.261947",
     "status": "completed"
    },
    "tags": []
   },
   "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>Age</th>\n",
       "      <th>Sex</th>\n",
       "      <th>HighChol</th>\n",
       "      <th>BMI</th>\n",
       "      <th>Smoker</th>\n",
       "      <th>PhysActivity</th>\n",
       "      <th>PhysHlth</th>\n",
       "      <th>Fruits</th>\n",
       "      <th>Veggies</th>\n",
       "      <th>HvyAlcoholConsump</th>\n",
       "      <th>Stroke</th>\n",
       "      <th>HighBP</th>\n",
       "      <th>Diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>13.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Age  Sex  HighChol   BMI  Smoker  PhysActivity  PhysHlth  Fruits  Veggies  \\\n",
       "0   4.0  1.0       0.0  26.0     0.0           1.0      30.0     0.0      1.0   \n",
       "1  12.0  1.0       1.0  26.0     1.0           0.0       0.0     1.0      0.0   \n",
       "2  13.0  1.0       0.0  26.0     0.0           1.0      10.0     1.0      1.0   \n",
       "3  11.0  1.0       1.0  28.0     1.0           1.0       3.0     1.0      1.0   \n",
       "4   8.0  0.0       0.0  29.0     1.0           1.0       0.0     1.0      1.0   \n",
       "\n",
       "   HvyAlcoholConsump  Stroke  HighBP  Diabetes  \n",
       "0                0.0     0.0     1.0       0.0  \n",
       "1                0.0     1.0     1.0       0.0  \n",
       "2                0.0     0.0     0.0       0.0  \n",
       "3                0.0     0.0     1.0       0.0  \n",
       "4                0.0     0.0     0.0       0.0  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#select variables that are medically likely to predict diabetes\n",
    "dm = dm_raw[[\"Age\",\"Sex\",\"HighChol\",\"BMI\",\"Smoker\",\"PhysActivity\",\"PhysHlth\",\"Fruits\",\"Veggies\",\"HvyAlcoholConsump\",\"Stroke\",\"HighBP\",\"Diabetes\"]]\n",
    "dm.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd9e101d",
   "metadata": {
    "papermill": {
     "duration": 0.016554,
     "end_time": "2023-02-14T22:16:26.349429",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.332875",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Brief data exploration**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "bf889d7c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:26.384749Z",
     "iopub.status.busy": "2023-02-14T22:16:26.384059Z",
     "iopub.status.idle": "2023-02-14T22:16:26.390116Z",
     "shell.execute_reply": "2023-02-14T22:16:26.389164Z"
    },
    "papermill": {
     "duration": 0.026407,
     "end_time": "2023-02-14T22:16:26.392426",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.366019",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(70692, 13)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5c13adf8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:26.428736Z",
     "iopub.status.busy": "2023-02-14T22:16:26.427955Z",
     "iopub.status.idle": "2023-02-14T22:16:26.464494Z",
     "shell.execute_reply": "2023-02-14T22:16:26.462466Z"
    },
    "papermill": {
     "duration": 0.058677,
     "end_time": "2023-02-14T22:16:26.468058",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.409381",
     "status": "completed"
    },
    "tags": []
   },
   "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>unique value count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sex</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HighChol</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Smoker</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PhysActivity</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PhysHlth</th>\n",
       "      <td>31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fruits</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Veggies</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HvyAlcoholConsump</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HighBP</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Diabetes</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   unique value count\n",
       "Age                                13\n",
       "Sex                                 2\n",
       "HighChol                            2\n",
       "BMI                                80\n",
       "Smoker                              2\n",
       "PhysActivity                        2\n",
       "PhysHlth                           31\n",
       "Fruits                              2\n",
       "Veggies                             2\n",
       "HvyAlcoholConsump                   2\n",
       "Stroke                              2\n",
       "HighBP                              2\n",
       "Diabetes                            2"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#check unique values\n",
    "\n",
    "unique_values = {}\n",
    "for col in dm.columns:\n",
    "    unique_values[col] = dm[col].value_counts().shape[0]\n",
    "\n",
    "pd.DataFrame(unique_values, index=['unique value count']).transpose()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e9c203e1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:26.504513Z",
     "iopub.status.busy": "2023-02-14T22:16:26.503702Z",
     "iopub.status.idle": "2023-02-14T22:16:29.120633Z",
     "shell.execute_reply": "2023-02-14T22:16:29.119076Z"
    },
    "papermill": {
     "duration": 2.639358,
     "end_time": "2023-02-14T22:16:29.125306",
     "exception": false,
     "start_time": "2023-02-14T22:16:26.485948",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2500x3500 with 13 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#check frequency of all values in the column\n",
    "\n",
    "# All data columns except for color\n",
    "feature_cols = [x for x in dm.columns if x not in 'stroke']\n",
    "plt.figure(figsize=(25,35))\n",
    "# loop for subplots\n",
    "for i in range(len(feature_cols)):\n",
    "    plt.subplot(8,5,i+1)\n",
    "    plt.title(feature_cols[i])\n",
    "    plt.xticks(rotation=90)\n",
    "    plt.hist(dm[feature_cols[i]],color = \"deepskyblue\")\n",
    "    \n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "01f502a9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:29.168176Z",
     "iopub.status.busy": "2023-02-14T22:16:29.166900Z",
     "iopub.status.idle": "2023-02-14T22:16:29.177383Z",
     "shell.execute_reply": "2023-02-14T22:16:29.176131Z"
    },
    "papermill": {
     "duration": 0.0343,
     "end_time": "2023-02-14T22:16:29.179954",
     "exception": false,
     "start_time": "2023-02-14T22:16:29.145654",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#we should drop the columns with very small categories- (HvyAlcoholConsump and stroke)\n",
    "dm.drop(['HvyAlcoholConsump','Stroke'], axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "b6608dc2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:29.220767Z",
     "iopub.status.busy": "2023-02-14T22:16:29.219390Z",
     "iopub.status.idle": "2023-02-14T22:16:29.533103Z",
     "shell.execute_reply": "2023-02-14T22:16:29.531890Z"
    },
    "papermill": {
     "duration": 0.336924,
     "end_time": "2023-02-14T22:16:29.535876",
     "exception": false,
     "start_time": "2023-02-14T22:16:29.198952",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#check correlation of other columns with diabetes column\n",
    "dm.drop('Diabetes', axis=1).corrwith(dm.Diabetes).plot(kind='bar', grid=True, figsize=(10, 6), title=\"Correlation with Diabetes\",color=\"deepskyblue\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "b1ca7290",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:29.575637Z",
     "iopub.status.busy": "2023-02-14T22:16:29.574891Z",
     "iopub.status.idle": "2023-02-14T22:16:29.580195Z",
     "shell.execute_reply": "2023-02-14T22:16:29.578923Z"
    },
    "papermill": {
     "duration": 0.027801,
     "end_time": "2023-02-14T22:16:29.582588",
     "exception": false,
     "start_time": "2023-02-14T22:16:29.554787",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#variables with correlation less than 0.1 are Sex, Smoker, Fruits, Veggies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "4f52de8b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:29.622149Z",
     "iopub.status.busy": "2023-02-14T22:16:29.621197Z",
     "iopub.status.idle": "2023-02-14T22:16:30.854592Z",
     "shell.execute_reply": "2023-02-14T22:16:30.853188Z"
    },
    "papermill": {
     "duration": 1.25755,
     "end_time": "2023-02-14T22:16:30.858779",
     "exception": false,
     "start_time": "2023-02-14T22:16:29.601229",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x1000 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Correlation between any two features\n",
    "# check for possible co-variates\n",
    "\n",
    "sns.set(rc = {'figure.figsize':(10,10)})\n",
    "sns.heatmap(dm.corr(),vmin=-1, vmax=1, annot = True, fmt='.1g',cmap= 'coolwarm')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "66a99128",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:30.908797Z",
     "iopub.status.busy": "2023-02-14T22:16:30.908053Z",
     "iopub.status.idle": "2023-02-14T22:16:30.916097Z",
     "shell.execute_reply": "2023-02-14T22:16:30.914834Z"
    },
    "papermill": {
     "duration": 0.03676,
     "end_time": "2023-02-14T22:16:30.919153",
     "exception": false,
     "start_time": "2023-02-14T22:16:30.882393",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#drop the variables with low correlations Sex, Smoker, Fruits, Veggies\n",
    "dm.drop(['Sex','Smoker','Fruits','Veggies'], axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7d30ade5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:30.976863Z",
     "iopub.status.busy": "2023-02-14T22:16:30.975330Z",
     "iopub.status.idle": "2023-02-14T22:16:31.000374Z",
     "shell.execute_reply": "2023-02-14T22:16:30.999025Z"
    },
    "papermill": {
     "duration": 0.059066,
     "end_time": "2023-02-14T22:16:31.003755",
     "exception": false,
     "start_time": "2023-02-14T22:16:30.944689",
     "status": "completed"
    },
    "tags": []
   },
   "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>Age</th>\n",
       "      <th>HighChol</th>\n",
       "      <th>BMI</th>\n",
       "      <th>PhysActivity</th>\n",
       "      <th>PhysHlth</th>\n",
       "      <th>HighBP</th>\n",
       "      <th>Diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>13.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Age  HighChol   BMI  PhysActivity  PhysHlth  HighBP  Diabetes\n",
       "0   4.0       0.0  26.0           1.0      30.0     1.0       0.0\n",
       "1  12.0       1.0  26.0           0.0       0.0     1.0       0.0\n",
       "2  13.0       0.0  26.0           1.0      10.0     0.0       0.0\n",
       "3  11.0       1.0  28.0           1.0       3.0     1.0       0.0\n",
       "4   8.0       0.0  29.0           1.0       0.0     0.0       0.0"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "af0bdb3e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:31.052052Z",
     "iopub.status.busy": "2023-02-14T22:16:31.051050Z",
     "iopub.status.idle": "2023-02-14T22:16:31.056983Z",
     "shell.execute_reply": "2023-02-14T22:16:31.055168Z"
    },
    "papermill": {
     "duration": 0.031912,
     "end_time": "2023-02-14T22:16:31.059694",
     "exception": false,
     "start_time": "2023-02-14T22:16:31.027782",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#narrowed down to 6 possible determinants \n",
    "#determine which predictors are more useful"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "75787771",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:31.110626Z",
     "iopub.status.busy": "2023-02-14T22:16:31.109741Z",
     "iopub.status.idle": "2023-02-14T22:16:31.951675Z",
     "shell.execute_reply": "2023-02-14T22:16:31.950668Z"
    },
    "papermill": {
     "duration": 0.873438,
     "end_time": "2023-02-14T22:16:31.954789",
     "exception": false,
     "start_time": "2023-02-14T22:16:31.081351",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 3000x2300 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Bivariate bar plot for categorical variables\n",
    "\n",
    "features = [x for x in dm.columns if x not in ['Age','BMI','PhysHlth','Diabetes']]\n",
    "plt.figure(figsize = (30,23))\n",
    "plt.suptitle('Diabetes by categorical features')\n",
    "\n",
    "#subplots\n",
    "for i in enumerate(features):\n",
    "    plt.subplot(2,4, i[0]+1)   \n",
    "    x = sns.countplot(data=dm, x=i[1], hue='Diabetes', palette = ['deepskyblue','crimson'])\n",
    "    for z in x.patches:\n",
    "      x.annotate('{:.1f}'.format((z.get_height()/dm.shape[0])*100)+'%',(z.get_x()+0.25, z.get_height()+0.01))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "68eed8e0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:32.002488Z",
     "iopub.status.busy": "2023-02-14T22:16:32.001719Z",
     "iopub.status.idle": "2023-02-14T22:16:33.114195Z",
     "shell.execute_reply": "2023-02-14T22:16:33.112964Z"
    },
    "papermill": {
     "duration": 1.138842,
     "end_time": "2023-02-14T22:16:33.116787",
     "exception": false,
     "start_time": "2023-02-14T22:16:31.977945",
     "status": "completed"
    },
    "scrolled": true,
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7f1d6d38a090>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 1200x500 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#for numeric variables\n",
    "plt.figure(figsize=(12,5))\n",
    "sns.displot(x='BMI', col='Diabetes' , data = dm, kind=\"kde\" ,color = 'deepskyblue')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "f6c23b04",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:33.165619Z",
     "iopub.status.busy": "2023-02-14T22:16:33.164777Z",
     "iopub.status.idle": "2023-02-14T22:16:34.236828Z",
     "shell.execute_reply": "2023-02-14T22:16:34.235515Z"
    },
    "papermill": {
     "duration": 1.099264,
     "end_time": "2023-02-14T22:16:34.239431",
     "exception": false,
     "start_time": "2023-02-14T22:16:33.140167",
     "status": "completed"
    },
    "scrolled": true,
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7f1d52a7e390>"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 1200x2000 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12,20))\n",
    "sns.displot(data=dm,col='Diabetes',x='Age',color='deepskyblue')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cde9b9b3",
   "metadata": {
    "papermill": {
     "duration": 0.025478,
     "end_time": "2023-02-14T22:16:34.288699",
     "exception": false,
     "start_time": "2023-02-14T22:16:34.263221",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Data transformation**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "0f6c1e1f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:34.340682Z",
     "iopub.status.busy": "2023-02-14T22:16:34.339954Z",
     "iopub.status.idle": "2023-02-14T22:16:34.362724Z",
     "shell.execute_reply": "2023-02-14T22:16:34.361420Z"
    },
    "papermill": {
     "duration": 0.052057,
     "end_time": "2023-02-14T22:16:34.365694",
     "exception": false,
     "start_time": "2023-02-14T22:16:34.313637",
     "status": "completed"
    },
    "tags": []
   },
   "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>skew</th>\n",
       "      <th>too_skewed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>-0.545923</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>1.719180</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PhysHlth</th>\n",
       "      <td>1.657304</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              skew  too_skewed\n",
       "Age      -0.545923       False\n",
       "BMI       1.719180        True\n",
       "PhysHlth  1.657304        True"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Check skewness\n",
    "#can only be checked for numeric data\n",
    "\n",
    "dm_skew = dm[['Age','BMI','PhysHlth']]\n",
    "skew = pd.DataFrame(dm_skew.skew())\n",
    "skew.columns = ['skew']\n",
    "skew['too_skewed'] = skew['skew'] > .75\n",
    "skew"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "18e09172",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:34.416141Z",
     "iopub.status.busy": "2023-02-14T22:16:34.415682Z",
     "iopub.status.idle": "2023-02-14T22:16:34.421101Z",
     "shell.execute_reply": "2023-02-14T22:16:34.419508Z"
    },
    "papermill": {
     "duration": 0.033341,
     "end_time": "2023-02-14T22:16:34.423866",
     "exception": false,
     "start_time": "2023-02-14T22:16:34.390525",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#BMI and PhysHlth are skewed. It needs to be transformed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "10773a7a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:34.475938Z",
     "iopub.status.busy": "2023-02-14T22:16:34.475475Z",
     "iopub.status.idle": "2023-02-14T22:16:34.510499Z",
     "shell.execute_reply": "2023-02-14T22:16:34.509003Z"
    },
    "papermill": {
     "duration": 0.064097,
     "end_time": "2023-02-14T22:16:34.512912",
     "exception": false,
     "start_time": "2023-02-14T22:16:34.448815",
     "status": "completed"
    },
    "tags": []
   },
   "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>Age</th>\n",
       "      <th>HighChol</th>\n",
       "      <th>BMI</th>\n",
       "      <th>PhysActivity</th>\n",
       "      <th>PhysHlth</th>\n",
       "      <th>HighBP</th>\n",
       "      <th>Diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.250000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.162791</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.916667</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.162791</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.162791</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.833333</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.186047</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.583333</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.197674</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Age  HighChol       BMI  PhysActivity  PhysHlth  HighBP  Diabetes\n",
       "0  0.250000       0.0  0.162791           1.0  1.000000     1.0       0.0\n",
       "1  0.916667       1.0  0.162791           0.0  0.000000     1.0       0.0\n",
       "2  1.000000       0.0  0.162791           1.0  0.333333     0.0       0.0\n",
       "3  0.833333       1.0  0.186047           1.0  0.100000     1.0       0.0\n",
       "4  0.583333       0.0  0.197674           1.0  0.000000     0.0       0.0"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Scaling the data for features selection using the MinMaxScaler method.\n",
    "#only numeric variables apply here\n",
    "\n",
    "mms = MinMaxScaler()\n",
    "dm[['BMI']] = mms.fit_transform(dm[['BMI']])\n",
    "dm[['Age']] = mms.fit_transform(dm[['Age']])\n",
    "dm[['PhysHlth']] = mms.fit_transform(dm[['PhysHlth']])\n",
    "dm.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "57ec7523",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:34.566043Z",
     "iopub.status.busy": "2023-02-14T22:16:34.565541Z",
     "iopub.status.idle": "2023-02-14T22:16:34.573856Z",
     "shell.execute_reply": "2023-02-14T22:16:34.572320Z"
    },
    "papermill": {
     "duration": 0.038582,
     "end_time": "2023-02-14T22:16:34.577006",
     "exception": false,
     "start_time": "2023-02-14T22:16:34.538424",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#Features selection -step 1\n",
    "#1. Define X,y\n",
    "y = (dm['Diabetes']).astype(int)\n",
    "X = dm.loc[:, dm.columns != 'Diabetes']  # everything except \"Diabetes\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "babc9b52",
   "metadata": {
    "papermill": {
     "duration": 0.024738,
     "end_time": "2023-02-14T22:16:34.626338",
     "exception": false,
     "start_time": "2023-02-14T22:16:34.601600",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Feature Selection**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "4c05d999",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:34.677645Z",
     "iopub.status.busy": "2023-02-14T22:16:34.677204Z",
     "iopub.status.idle": "2023-02-14T22:16:40.784910Z",
     "shell.execute_reply": "2023-02-14T22:16:40.783617Z"
    },
    "papermill": {
     "duration": 6.137223,
     "end_time": "2023-02-14T22:16:40.787876",
     "exception": false,
     "start_time": "2023-02-14T22:16:34.650653",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.15190905 0.11040928 0.34254753 0.0242652  0.14311465 0.22775429]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#step 2\n",
    "\n",
    "model = ExtraTreesClassifier()\n",
    "model.fit(X,y)\n",
    "print(model.feature_importances_) #use inbuilt class feature_importances of tree based classifiers\n",
    "#plot graph of feature importances for better visualization\n",
    "feat_importances = pd.Series(model.feature_importances_, index=X.columns)\n",
    "plt.figure(figsize=(8,6))\n",
    "feat_importances.nlargest(6).plot(kind='barh')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "4748998e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:40.839347Z",
     "iopub.status.busy": "2023-02-14T22:16:40.838205Z",
     "iopub.status.idle": "2023-02-14T22:16:40.867711Z",
     "shell.execute_reply": "2023-02-14T22:16:40.865609Z"
    },
    "papermill": {
     "duration": 0.058944,
     "end_time": "2023-02-14T22:16:40.871339",
     "exception": false,
     "start_time": "2023-02-14T22:16:40.812395",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          Specs        Score\n",
      "5        HighBP  4491.799960\n",
      "1      HighChol  2804.501278\n",
      "4      PhysHlth  1864.301775\n",
      "3  PhysActivity   528.494034\n",
      "0           Age   490.930094\n",
      "2           BMI   200.502204\n"
     ]
    }
   ],
   "source": [
    "#method 2   \n",
    "\n",
    "#apply SelectKBest class to extract top 5 best features   #Do this before quantile transformation\n",
    "bestfeatures = SelectKBest(score_func=chi2, k=5)\n",
    "fit = bestfeatures.fit(X,y)\n",
    "dfscores = pd.DataFrame(fit.scores_)\n",
    "dfcolumns = pd.DataFrame(X.columns)\n",
    "#concat two dataframes for better visualization \n",
    "featureScores = pd.concat([dfcolumns,dfscores],axis=1)\n",
    "featureScores.columns = ['Specs','Score']  #naming the dataframe columns\n",
    "print(featureScores.nlargest(6,'Score'))  #print 5 best features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "2478100e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:16:40.956480Z",
     "iopub.status.busy": "2023-02-14T22:16:40.955628Z",
     "iopub.status.idle": "2023-02-14T22:17:03.458858Z",
     "shell.execute_reply": "2023-02-14T22:17:03.457946Z"
    },
    "papermill": {
     "duration": 22.632895,
     "end_time": "2023-02-14T22:17:03.549127",
     "exception": false,
     "start_time": "2023-02-14T22:16:40.916232",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Features: 62/62"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best accuracy score: 0.72\n",
      "Best subset (indices): (0, 1, 2, 4, 5)\n",
      "Best subset (corresponding names): ('Age', 'HighChol', 'BMI', 'PhysHlth', 'HighBP')\n"
     ]
    }
   ],
   "source": [
    "#Method 3\n",
    "\n",
    "#Create a logistic regression classifier\n",
    "lr = LogisticRegression()\n",
    "# Create an EFS object\n",
    "efs = EFS(estimator=lr,        # Use logistic regression as the classifier/estimator\n",
    "          min_features=1,      # The minimum number of features to consider is 1\n",
    "          max_features=5,      # The maximum number of features to consider is 5\n",
    "          scoring='accuracy',  # The metric to use to evaluate the classifier is accuracy \n",
    "          cv=4)                # The number of cross-validations to perform is 4\n",
    "\n",
    "# Train EFS with our dataset\n",
    "efs = efs.fit(X, y)\n",
    "# Print the results\n",
    "print('Best accuracy score: %.2f' % efs.best_score_) # best_score_ shows the best score \n",
    "print('Best subset (indices):', efs.best_idx_)       # best_idx_ shows the index of features that yield the best score \n",
    "print('Best subset (corresponding names):', efs.best_feature_names_) # best_feature_names_ shows the feature names "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "bf0bffcf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:03.612401Z",
     "iopub.status.busy": "2023-02-14T22:17:03.611887Z",
     "iopub.status.idle": "2023-02-14T22:17:03.634436Z",
     "shell.execute_reply": "2023-02-14T22:17:03.633136Z"
    },
    "papermill": {
     "duration": 0.057328,
     "end_time": "2023-02-14T22:17:03.637079",
     "exception": false,
     "start_time": "2023-02-14T22:17:03.579751",
     "status": "completed"
    },
    "tags": []
   },
   "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>skew</th>\n",
       "      <th>too_skewed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>-0.545923</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>1.719180</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PhysHlth</th>\n",
       "      <td>1.657304</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              skew  too_skewed\n",
       "Age      -0.545923       False\n",
       "BMI       1.719180        True\n",
       "PhysHlth  1.657304        True"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#recheck the skew\n",
    "dm_skew = dm[['Age','BMI','PhysHlth']]\n",
    "skew = pd.DataFrame(dm_skew.skew())\n",
    "skew.columns = ['skew']\n",
    "skew['too_skewed'] = skew['skew'] > .75\n",
    "skew"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "4f17dc4f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:03.700474Z",
     "iopub.status.busy": "2023-02-14T22:17:03.699811Z",
     "iopub.status.idle": "2023-02-14T22:17:03.752711Z",
     "shell.execute_reply": "2023-02-14T22:17:03.751129Z"
    },
    "papermill": {
     "duration": 0.087804,
     "end_time": "2023-02-14T22:17:03.755737",
     "exception": false,
     "start_time": "2023-02-14T22:17:03.667933",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#use quantile tranformation\n",
    "\n",
    "qt = QuantileTransformer(n_quantiles=500, output_distribution='normal')\n",
    "dm[['BMI']] = qt.fit_transform(dm[['BMI']])\n",
    "dm[['PhysHlth']] = qt.fit_transform(dm[['PhysHlth']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "3e48ae6d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:03.819821Z",
     "iopub.status.busy": "2023-02-14T22:17:03.819288Z",
     "iopub.status.idle": "2023-02-14T22:17:03.838726Z",
     "shell.execute_reply": "2023-02-14T22:17:03.837153Z"
    },
    "papermill": {
     "duration": 0.055694,
     "end_time": "2023-02-14T22:17:03.841707",
     "exception": false,
     "start_time": "2023-02-14T22:17:03.786013",
     "status": "completed"
    },
    "tags": []
   },
   "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>skew</th>\n",
       "      <th>too_skewed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>-0.545923</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>0.016868</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PhysHlth</th>\n",
       "      <td>0.693496</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              skew  too_skewed\n",
       "Age      -0.545923       False\n",
       "BMI       0.016868       False\n",
       "PhysHlth  0.693496       False"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#recheck the skew\n",
    "dm_skew = dm[['Age','BMI','PhysHlth']]\n",
    "skew = pd.DataFrame(dm_skew.skew())\n",
    "skew.columns = ['skew']\n",
    "skew['too_skewed'] = skew['skew'] > .75\n",
    "skew"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "1659175b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:03.903622Z",
     "iopub.status.busy": "2023-02-14T22:17:03.903121Z",
     "iopub.status.idle": "2023-02-14T22:17:03.920800Z",
     "shell.execute_reply": "2023-02-14T22:17:03.919402Z"
    },
    "papermill": {
     "duration": 0.051924,
     "end_time": "2023-02-14T22:17:03.923420",
     "exception": false,
     "start_time": "2023-02-14T22:17:03.871496",
     "status": "completed"
    },
    "tags": []
   },
   "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>Age</th>\n",
       "      <th>HighChol</th>\n",
       "      <th>BMI</th>\n",
       "      <th>PhysActivity</th>\n",
       "      <th>PhysHlth</th>\n",
       "      <th>HighBP</th>\n",
       "      <th>Diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.250000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.505473</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5.199338</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.916667</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.505473</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-5.199338</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.505473</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.822449</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.833333</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.093065</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.468708</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.583333</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.065349</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-5.199338</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Age  HighChol       BMI  PhysActivity  PhysHlth  HighBP  Diabetes\n",
       "0  0.250000       0.0 -0.505473           1.0  5.199338     1.0       0.0\n",
       "1  0.916667       1.0 -0.505473           0.0 -5.199338     1.0       0.0\n",
       "2  1.000000       0.0 -0.505473           1.0  0.822449     0.0       0.0\n",
       "3  0.833333       1.0 -0.093065           1.0  0.468708     1.0       0.0\n",
       "4  0.583333       0.0  0.065349           1.0 -5.199338     0.0       0.0"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f10cb323",
   "metadata": {
    "papermill": {
     "duration": 0.030163,
     "end_time": "2023-02-14T22:17:03.984434",
     "exception": false,
     "start_time": "2023-02-14T22:17:03.954271",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Model building and testing**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "eed23aa6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:04.044947Z",
     "iopub.status.busy": "2023-02-14T22:17:04.044477Z",
     "iopub.status.idle": "2023-02-14T22:17:04.064359Z",
     "shell.execute_reply": "2023-02-14T22:17:04.063367Z"
    },
    "papermill": {
     "duration": 0.053942,
     "end_time": "2023-02-14T22:17:04.067164",
     "exception": false,
     "start_time": "2023-02-14T22:17:04.013222",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#Data splitting\n",
    "\n",
    "y = (dm['Diabetes']).astype(int)\n",
    "X = dm.loc[:, dm.columns != 'stroke']  # everything except \"stroke\"\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "303a1c0f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:04.128305Z",
     "iopub.status.busy": "2023-02-14T22:17:04.126988Z",
     "iopub.status.idle": "2023-02-14T22:17:04.135011Z",
     "shell.execute_reply": "2023-02-14T22:17:04.133776Z"
    },
    "papermill": {
     "duration": 0.041082,
     "end_time": "2023-02-14T22:17:04.137296",
     "exception": false,
     "start_time": "2023-02-14T22:17:04.096214",
     "status": "completed"
    },
    "scrolled": true,
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(49484, 7)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "18fc16ac",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:04.198252Z",
     "iopub.status.busy": "2023-02-14T22:17:04.196919Z",
     "iopub.status.idle": "2023-02-14T22:17:04.205591Z",
     "shell.execute_reply": "2023-02-14T22:17:04.204291Z"
    },
    "papermill": {
     "duration": 0.041391,
     "end_time": "2023-02-14T22:17:04.208138",
     "exception": false,
     "start_time": "2023-02-14T22:17:04.166747",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(21208, 7)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "c20ea129",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:04.271044Z",
     "iopub.status.busy": "2023-02-14T22:17:04.270283Z",
     "iopub.status.idle": "2023-02-14T22:17:04.274757Z",
     "shell.execute_reply": "2023-02-14T22:17:04.273820Z"
    },
    "papermill": {
     "duration": 0.038742,
     "end_time": "2023-02-14T22:17:04.277122",
     "exception": false,
     "start_time": "2023-02-14T22:17:04.238380",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#Predict with Decision tree, KNN and Extra Tree"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e9553f3",
   "metadata": {
    "papermill": {
     "duration": 0.030118,
     "end_time": "2023-02-14T22:17:04.337314",
     "exception": false,
     "start_time": "2023-02-14T22:17:04.307196",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## K Nearest Neighbors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "8008e4c2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:04.399016Z",
     "iopub.status.busy": "2023-02-14T22:17:04.398054Z",
     "iopub.status.idle": "2023-02-14T22:17:56.949308Z",
     "shell.execute_reply": "2023-02-14T22:17:56.947187Z"
    },
    "papermill": {
     "duration": 52.585491,
     "end_time": "2023-02-14T22:17:56.952417",
     "exception": false,
     "start_time": "2023-02-14T22:17:04.366926",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 20 candidates, totalling 100 fits\n",
      "[CV 1/5] END ...n_neighbors=1, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 2/5] END ...n_neighbors=1, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 3/5] END ...n_neighbors=1, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 4/5] END ...n_neighbors=1, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 5/5] END ...n_neighbors=1, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 1/5] END ....n_neighbors=1, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 2/5] END ....n_neighbors=1, weights=uniform;, score=1.000 total time=   0.5s\n",
      "[CV 3/5] END ....n_neighbors=1, weights=uniform;, score=1.000 total time=   0.5s\n",
      "[CV 4/5] END ....n_neighbors=1, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 5/5] END ....n_neighbors=1, weights=uniform;, score=1.000 total time=   0.5s\n",
      "[CV 1/5] END ...n_neighbors=3, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 2/5] END ...n_neighbors=3, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 3/5] END ...n_neighbors=3, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 4/5] END ...n_neighbors=3, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 5/5] END ...n_neighbors=3, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 1/5] END ....n_neighbors=3, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 2/5] END ....n_neighbors=3, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 3/5] END ....n_neighbors=3, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 4/5] END ....n_neighbors=3, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 5/5] END ....n_neighbors=3, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 1/5] END ...n_neighbors=5, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 2/5] END ...n_neighbors=5, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 3/5] END ...n_neighbors=5, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 4/5] END ...n_neighbors=5, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 5/5] END ...n_neighbors=5, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 1/5] END ....n_neighbors=5, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 2/5] END ....n_neighbors=5, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 3/5] END ....n_neighbors=5, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 4/5] END ....n_neighbors=5, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 5/5] END ....n_neighbors=5, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 1/5] END ...n_neighbors=7, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 2/5] END ...n_neighbors=7, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 3/5] END ...n_neighbors=7, weights=distance;, score=1.000 total time=   0.3s\n",
      "[CV 4/5] END ...n_neighbors=7, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 5/5] END ...n_neighbors=7, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 1/5] END ....n_neighbors=7, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 2/5] END ....n_neighbors=7, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 3/5] END ....n_neighbors=7, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 4/5] END ....n_neighbors=7, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 5/5] END ....n_neighbors=7, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 1/5] END ...n_neighbors=9, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 2/5] END ...n_neighbors=9, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 3/5] END ...n_neighbors=9, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 4/5] END ...n_neighbors=9, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 5/5] END ...n_neighbors=9, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 1/5] END ....n_neighbors=9, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 2/5] END ....n_neighbors=9, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 3/5] END ....n_neighbors=9, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 4/5] END ....n_neighbors=9, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 5/5] END ....n_neighbors=9, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 1/5] END ..n_neighbors=11, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 2/5] END ..n_neighbors=11, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 3/5] END ..n_neighbors=11, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 4/5] END ..n_neighbors=11, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 5/5] END ..n_neighbors=11, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 1/5] END ...n_neighbors=11, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 2/5] END ...n_neighbors=11, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 3/5] END ...n_neighbors=11, weights=uniform;, score=1.000 total time=   0.6s\n",
      "[CV 4/5] END ...n_neighbors=11, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 5/5] END ...n_neighbors=11, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 1/5] END ..n_neighbors=13, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 2/5] END ..n_neighbors=13, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 3/5] END ..n_neighbors=13, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 4/5] END ..n_neighbors=13, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 5/5] END ..n_neighbors=13, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 1/5] END ...n_neighbors=13, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 2/5] END ...n_neighbors=13, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 3/5] END ...n_neighbors=13, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 4/5] END ...n_neighbors=13, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 5/5] END ...n_neighbors=13, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 1/5] END ..n_neighbors=15, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 2/5] END ..n_neighbors=15, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 3/5] END ..n_neighbors=15, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 4/5] END ..n_neighbors=15, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 5/5] END ..n_neighbors=15, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 1/5] END ...n_neighbors=15, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 2/5] END ...n_neighbors=15, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 3/5] END ...n_neighbors=15, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 4/5] END ...n_neighbors=15, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 5/5] END ...n_neighbors=15, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 1/5] END ..n_neighbors=17, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 2/5] END ..n_neighbors=17, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 3/5] END ..n_neighbors=17, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 4/5] END ..n_neighbors=17, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 5/5] END ..n_neighbors=17, weights=distance;, score=1.000 total time=   0.4s\n",
      "[CV 1/5] END ...n_neighbors=17, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 2/5] END ...n_neighbors=17, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 3/5] END ...n_neighbors=17, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 4/5] END ...n_neighbors=17, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 5/5] END ...n_neighbors=17, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 1/5] END ..n_neighbors=19, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 2/5] END ..n_neighbors=19, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 3/5] END ..n_neighbors=19, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 4/5] END ..n_neighbors=19, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 5/5] END ..n_neighbors=19, weights=distance;, score=1.000 total time=   0.5s\n",
      "[CV 1/5] END ...n_neighbors=19, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 2/5] END ...n_neighbors=19, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 3/5] END ...n_neighbors=19, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 4/5] END ...n_neighbors=19, weights=uniform;, score=1.000 total time=   0.7s\n",
      "[CV 5/5] END ...n_neighbors=19, weights=uniform;, score=1.000 total time=   0.7s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "GridSearchCV(estimator=KNeighborsClassifier(),\n",
       "             param_grid={'n_neighbors': [1, 3, 5, 7, 9, 11, 13, 15, 17, 19],\n",
       "                         'weights': ['distance', 'uniform']},\n",
       "             verbose=3)"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "# defining parameter range\n",
    "param_grid = {'n_neighbors': [1,3,5,7,9,11,13,15,17,19],  #odd numbers because there are 2 classes in target coulmn\n",
    "              'weights': ['distance', 'uniform']}  \n",
    "gridKNN = GridSearchCV(KNeighborsClassifier(), param_grid, refit = True, verbose = 3)\n",
    "  \n",
    "# fitting the model for grid search\n",
    "gridKNN.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "6b9f110b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:57.030697Z",
     "iopub.status.busy": "2023-02-14T22:17:57.029372Z",
     "iopub.status.idle": "2023-02-14T22:17:57.037366Z",
     "shell.execute_reply": "2023-02-14T22:17:57.035967Z"
    },
    "papermill": {
     "duration": 0.050482,
     "end_time": "2023-02-14T22:17:57.040632",
     "exception": false,
     "start_time": "2023-02-14T22:17:56.990150",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'n_neighbors': 1, 'weights': 'distance'}\n"
     ]
    }
   ],
   "source": [
    "print(gridKNN.best_params_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "eddfdf7c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:57.124799Z",
     "iopub.status.busy": "2023-02-14T22:17:57.124234Z",
     "iopub.status.idle": "2023-02-14T22:17:58.949956Z",
     "shell.execute_reply": "2023-02-14T22:17:58.948501Z"
    },
    "papermill": {
     "duration": 1.870434,
     "end_time": "2023-02-14T22:17:58.952830",
     "exception": false,
     "start_time": "2023-02-14T22:17:57.082396",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#predict with the best parameter\n",
    "y_pred_test = gridKNN.predict(X_test)\n",
    "y_pred_train = gridKNN.predict(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "13a21dc9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:59.026275Z",
     "iopub.status.busy": "2023-02-14T22:17:59.025884Z",
     "iopub.status.idle": "2023-02-14T22:17:59.037797Z",
     "shell.execute_reply": "2023-02-14T22:17:59.036830Z"
    },
    "papermill": {
     "duration": 0.051517,
     "end_time": "2023-02-14T22:17:59.040342",
     "exception": false,
     "start_time": "2023-02-14T22:17:58.988825",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "0.9999528479818937\n"
     ]
    }
   ],
   "source": [
    "#Check accuracy and overfitting\n",
    "print(accuracy_score(y_train, y_pred_train))\n",
    "print(accuracy_score(y_test, y_pred_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "4433f96e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:59.117976Z",
     "iopub.status.busy": "2023-02-14T22:17:59.117481Z",
     "iopub.status.idle": "2023-02-14T22:17:59.380148Z",
     "shell.execute_reply": "2023-02-14T22:17:59.378802Z"
    },
    "papermill": {
     "duration": 0.305914,
     "end_time": "2023-02-14T22:17:59.383120",
     "exception": false,
     "start_time": "2023-02-14T22:17:59.077206",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 500x500 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 600x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#confusion matrix\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
    "cm = confusion_matrix(y_test, y_pred_test, labels=gridKNN.classes_)\n",
    "disp = ConfusionMatrixDisplay(confusion_matrix=cm,display_labels=gridKNN.classes_)\n",
    "fig = plt.figure(figsize=(5, 5))\n",
    "disp.plot(cmap=plt.cm.Blues) \n",
    "plt.grid(which='major')     #remove cell gridlines\n",
    "plt.gcf().set_size_inches(6, 6)   # Adjust the size of the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "400f3a5e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:59.461767Z",
     "iopub.status.busy": "2023-02-14T22:17:59.460484Z",
     "iopub.status.idle": "2023-02-14T22:17:59.468066Z",
     "shell.execute_reply": "2023-02-14T22:17:59.467140Z"
    },
    "papermill": {
     "duration": 0.049961,
     "end_time": "2023-02-14T22:17:59.470623",
     "exception": false,
     "start_time": "2023-02-14T22:17:59.420662",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#model metrics\n",
    "\n",
    "#function that get y_test and calculate into df all the relevant metric\n",
    "def train_evaluate_model(y_test):\n",
    "    #fit the model instance \n",
    "    predictions = y_pred_test # calculate predictions\n",
    "\n",
    "    #compute metrics for evaluation\n",
    "    accuracy = accuracy_score(y_test, predictions)\n",
    "    f1 = f1_score(y_test, predictions)\n",
    "    precision = precision_score(y_test, predictions)\n",
    "    recall = recall_score(y_test, predictions)\n",
    "    balanced_accuracy = balanced_accuracy_score(y_test, predictions)\n",
    "    auc = roc_auc_score(y_test, predictions)\n",
    "\n",
    "    #create a dataframe to visualize the results\n",
    "    eval_df = pd.DataFrame([[accuracy, f1, precision, recall, balanced_accuracy, auc]], columns=['accuracy', 'f1_score', 'precision', 'recall', 'balanced_accuracy', 'auc'])\n",
    "    return eval_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "ea305db6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:59.547500Z",
     "iopub.status.busy": "2023-02-14T22:17:59.546597Z",
     "iopub.status.idle": "2023-02-14T22:17:59.669400Z",
     "shell.execute_reply": "2023-02-14T22:17:59.667715Z"
    },
    "papermill": {
     "duration": 0.164792,
     "end_time": "2023-02-14T22:17:59.672586",
     "exception": false,
     "start_time": "2023-02-14T22:17:59.507794",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_dca02_row0_col0, #T_dca02_row0_col1, #T_dca02_row0_col2, #T_dca02_row0_col3, #T_dca02_row0_col4, #T_dca02_row0_col5 {\n",
       "  background-color: #008000;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_dca02_\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th class=\"col_heading level0 col0\" >accuracy</th>\n",
       "      <th class=\"col_heading level0 col1\" >f1_score</th>\n",
       "      <th class=\"col_heading level0 col2\" >precision</th>\n",
       "      <th class=\"col_heading level0 col3\" >recall</th>\n",
       "      <th class=\"col_heading level0 col4\" >balanced_accuracy</th>\n",
       "      <th class=\"col_heading level0 col5\" >auc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_dca02_level0_row0\" class=\"row_heading level0 row0\" >K Nearest Neighbors - Method 1</th>\n",
       "      <td id=\"T_dca02_row0_col0\" class=\"data row0 col0\" >0.999953</td>\n",
       "      <td id=\"T_dca02_row0_col1\" class=\"data row0 col1\" >0.999953</td>\n",
       "      <td id=\"T_dca02_row0_col2\" class=\"data row0 col2\" >0.999906</td>\n",
       "      <td id=\"T_dca02_row0_col3\" class=\"data row0 col3\" >1.000000</td>\n",
       "      <td id=\"T_dca02_row0_col4\" class=\"data row0 col4\" >0.999953</td>\n",
       "      <td id=\"T_dca02_row0_col5\" class=\"data row0 col5\" >0.999953</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7f1d4847d990>"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#model metrics\n",
    "\n",
    "results = train_evaluate_model(y_test)\n",
    "results.index = ['K Nearest Neighbors - Method 1']\n",
    "results.style.background_gradient(cmap = sns.color_palette(\"blend:green,red\", as_cmap=True))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d1e4199",
   "metadata": {
    "papermill": {
     "duration": 0.037508,
     "end_time": "2023-02-14T22:17:59.748173",
     "exception": false,
     "start_time": "2023-02-14T22:17:59.710665",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "ca40c087",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:59.824349Z",
     "iopub.status.busy": "2023-02-14T22:17:59.823630Z",
     "iopub.status.idle": "2023-02-14T22:17:59.846709Z",
     "shell.execute_reply": "2023-02-14T22:17:59.845420Z"
    },
    "papermill": {
     "duration": 0.064753,
     "end_time": "2023-02-14T22:17:59.849336",
     "exception": false,
     "start_time": "2023-02-14T22:17:59.784583",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "dt = DecisionTreeClassifier(random_state=42)\n",
    "dt = dt.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "2f3e83a9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:17:59.924861Z",
     "iopub.status.busy": "2023-02-14T22:17:59.924053Z",
     "iopub.status.idle": "2023-02-14T22:18:02.279827Z",
     "shell.execute_reply": "2023-02-14T22:18:02.278064Z"
    },
    "papermill": {
     "duration": 2.398145,
     "end_time": "2023-02-14T22:18:02.284336",
     "exception": false,
     "start_time": "2023-02-14T22:17:59.886191",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(estimator=DecisionTreeClassifier(random_state=42), n_jobs=-1,\n",
       "             param_grid={'max_depth': range(1, 2, 2),\n",
       "                         'max_features': range(1, 8)})"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#dt = DecisionTreeClassifier(random_state=42)\n",
    "dt = dt.fit(X_train, y_train)\n",
    "\n",
    "# defining parameter range\n",
    "param_grid = {'max_depth':range(1, dt.tree_.max_depth+1, 2),\n",
    "              'max_features': range(1, len(dt.feature_importances_)+1)}  \n",
    "gridDT = GridSearchCV(DecisionTreeClassifier(random_state=42), param_grid, n_jobs=-1)\n",
    "  \n",
    "# fitting the model for grid search\n",
    "gridDT.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "21ee24ac",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:18:02.363671Z",
     "iopub.status.busy": "2023-02-14T22:18:02.363190Z",
     "iopub.status.idle": "2023-02-14T22:18:02.370490Z",
     "shell.execute_reply": "2023-02-14T22:18:02.369034Z"
    },
    "papermill": {
     "duration": 0.051104,
     "end_time": "2023-02-14T22:18:02.373330",
     "exception": false,
     "start_time": "2023-02-14T22:18:02.322226",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'max_depth': 1, 'max_features': 1}\n"
     ]
    }
   ],
   "source": [
    "print(gridDT.best_params_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "3f351a15",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:18:02.450091Z",
     "iopub.status.busy": "2023-02-14T22:18:02.449669Z",
     "iopub.status.idle": "2023-02-14T22:18:02.463665Z",
     "shell.execute_reply": "2023-02-14T22:18:02.462123Z"
    },
    "papermill": {
     "duration": 0.057485,
     "end_time": "2023-02-14T22:18:02.466928",
     "exception": false,
     "start_time": "2023-02-14T22:18:02.409443",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "y_pred_test = gridDT.predict(X_test)\n",
    "y_pred_train = gridDT.predict(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "1bf162c9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:18:02.543243Z",
     "iopub.status.busy": "2023-02-14T22:18:02.542797Z",
     "iopub.status.idle": "2023-02-14T22:18:02.557537Z",
     "shell.execute_reply": "2023-02-14T22:18:02.555973Z"
    },
    "papermill": {
     "duration": 0.056219,
     "end_time": "2023-02-14T22:18:02.560411",
     "exception": false,
     "start_time": "2023-02-14T22:18:02.504192",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "1.0\n"
     ]
    }
   ],
   "source": [
    "print(accuracy_score(y_train, y_pred_train))\n",
    "print(accuracy_score(y_test, y_pred_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "1c64b340",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:18:02.641051Z",
     "iopub.status.busy": "2023-02-14T22:18:02.640532Z",
     "iopub.status.idle": "2023-02-14T22:18:02.910070Z",
     "shell.execute_reply": "2023-02-14T22:18:02.908656Z"
    },
    "papermill": {
     "duration": 0.313337,
     "end_time": "2023-02-14T22:18:02.912772",
     "exception": false,
     "start_time": "2023-02-14T22:18:02.599435",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 500x500 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 600x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#confusion matrix\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
    "cm = confusion_matrix(y_test, y_pred_test, labels=gridDT.classes_)\n",
    "disp = ConfusionMatrixDisplay(confusion_matrix=cm,display_labels=gridDT.classes_)\n",
    "fig = plt.figure(figsize=(5, 5))\n",
    "disp.plot(cmap=plt.cm.Blues) \n",
    "plt.grid(which='major')     #remove cell gridlines\n",
    "plt.gcf().set_size_inches(6, 6)   # Adjust the size of the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "afa471ca",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:18:02.989874Z",
     "iopub.status.busy": "2023-02-14T22:18:02.989412Z",
     "iopub.status.idle": "2023-02-14T22:18:03.052431Z",
     "shell.execute_reply": "2023-02-14T22:18:03.051556Z"
    },
    "papermill": {
     "duration": 0.104479,
     "end_time": "2023-02-14T22:18:03.054777",
     "exception": false,
     "start_time": "2023-02-14T22:18:02.950298",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_607fb_row0_col0, #T_607fb_row0_col1, #T_607fb_row0_col2, #T_607fb_row0_col3, #T_607fb_row0_col4, #T_607fb_row0_col5, #T_607fb_row1_col3 {\n",
       "  background-color: #ff0000;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_607fb_row1_col0, #T_607fb_row1_col1, #T_607fb_row1_col2, #T_607fb_row1_col4, #T_607fb_row1_col5 {\n",
       "  background-color: #008000;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_607fb_\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th class=\"col_heading level0 col0\" >accuracy</th>\n",
       "      <th class=\"col_heading level0 col1\" >f1_score</th>\n",
       "      <th class=\"col_heading level0 col2\" >precision</th>\n",
       "      <th class=\"col_heading level0 col3\" >recall</th>\n",
       "      <th class=\"col_heading level0 col4\" >balanced_accuracy</th>\n",
       "      <th class=\"col_heading level0 col5\" >auc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_607fb_level0_row0\" class=\"row_heading level0 row0\" >K Nearest Neighbors - Method 1</th>\n",
       "      <td id=\"T_607fb_row0_col0\" class=\"data row0 col0\" >0.999953</td>\n",
       "      <td id=\"T_607fb_row0_col1\" class=\"data row0 col1\" >0.999953</td>\n",
       "      <td id=\"T_607fb_row0_col2\" class=\"data row0 col2\" >0.999906</td>\n",
       "      <td id=\"T_607fb_row0_col3\" class=\"data row0 col3\" >1.000000</td>\n",
       "      <td id=\"T_607fb_row0_col4\" class=\"data row0 col4\" >0.999953</td>\n",
       "      <td id=\"T_607fb_row0_col5\" class=\"data row0 col5\" >0.999953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_607fb_level0_row1\" class=\"row_heading level0 row1\" >Decision Trees - Method 2</th>\n",
       "      <td id=\"T_607fb_row1_col0\" class=\"data row1 col0\" >1.000000</td>\n",
       "      <td id=\"T_607fb_row1_col1\" class=\"data row1 col1\" >1.000000</td>\n",
       "      <td id=\"T_607fb_row1_col2\" class=\"data row1 col2\" >1.000000</td>\n",
       "      <td id=\"T_607fb_row1_col3\" class=\"data row1 col3\" >1.000000</td>\n",
       "      <td id=\"T_607fb_row1_col4\" class=\"data row1 col4\" >1.000000</td>\n",
       "      <td id=\"T_607fb_row1_col5\" class=\"data row1 col5\" >1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7f1d48439110>"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "resultsDT = train_evaluate_model(y_test)\n",
    "resultsDT.index = ['Decision Trees - Method 2']\n",
    "results = results.append(resultsDT)\n",
    "results.style.background_gradient(cmap = sns.color_palette(\"blend:red,green\", as_cmap=True))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "496b323b",
   "metadata": {
    "id": "CfU8PTIwIZtU",
    "papermill": {
     "duration": 0.03703,
     "end_time": "2023-02-14T22:18:03.130002",
     "exception": false,
     "start_time": "2023-02-14T22:18:03.092972",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "11cedb46",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:18:03.208261Z",
     "iopub.status.busy": "2023-02-14T22:18:03.207178Z",
     "iopub.status.idle": "2023-02-14T22:19:21.187024Z",
     "shell.execute_reply": "2023-02-14T22:19:21.185739Z"
    },
    "id": "6zTlrL23IZtU",
    "outputId": "5b8b686e-e937-46d6-df0c-6f1196359ec8",
    "papermill": {
     "duration": 78.059116,
     "end_time": "2023-02-14T22:19:21.226383",
     "exception": false,
     "start_time": "2023-02-14T22:18:03.167267",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(estimator=RandomForestClassifier(n_jobs=-1, oob_score=True,\n",
       "                                              random_state=42,\n",
       "                                              warm_start=True),\n",
       "             param_grid={'n_estimators': [15, 20, 30, 40, 50, 100, 150, 200,\n",
       "                                          300, 400]})"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "RF = RandomForestClassifier(oob_score=True, \n",
    "                            random_state=42, \n",
    "                            warm_start=True,\n",
    "                            n_jobs=-1)\n",
    "\n",
    "# defining parameter range\n",
    "param_grid = {'n_estimators':[15, 20, 30, 40, 50, 100, 150, 200, 300, 400]\n",
    "              }  \n",
    "gridRF = GridSearchCV(RF, param_grid)\n",
    "  \n",
    "# fitting the model for grid search\n",
    "gridRF.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "d2ed7ef4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:19:21.305919Z",
     "iopub.status.busy": "2023-02-14T22:19:21.305472Z",
     "iopub.status.idle": "2023-02-14T22:19:21.311513Z",
     "shell.execute_reply": "2023-02-14T22:19:21.310156Z"
    },
    "id": "9qm1aWysIZtU",
    "outputId": "098a5119-febd-430b-9199-37f7a8557a29",
    "papermill": {
     "duration": 0.049836,
     "end_time": "2023-02-14T22:19:21.315005",
     "exception": false,
     "start_time": "2023-02-14T22:19:21.265169",
     "status": "completed"
    },
    "scrolled": true,
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'n_estimators': 15}\n"
     ]
    }
   ],
   "source": [
    "print(gridRF.best_params_)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2dc412cc",
   "metadata": {
    "id": "JrkLgC42IZtU",
    "papermill": {
     "duration": 0.038137,
     "end_time": "2023-02-14T22:19:21.390769",
     "exception": false,
     "start_time": "2023-02-14T22:19:21.352632",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Prediction according to this model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "3ff53dd6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:19:21.470370Z",
     "iopub.status.busy": "2023-02-14T22:19:21.469084Z",
     "iopub.status.idle": "2023-02-14T22:19:21.688389Z",
     "shell.execute_reply": "2023-02-14T22:19:21.687312Z"
    },
    "id": "5qfCWalSIZtV",
    "papermill": {
     "duration": 0.26264,
     "end_time": "2023-02-14T22:19:21.691311",
     "exception": false,
     "start_time": "2023-02-14T22:19:21.428671",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "y_pred_test = gridRF.predict(X_test)\n",
    "y_pred_train = gridRF.predict(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "c836d55d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:19:21.770319Z",
     "iopub.status.busy": "2023-02-14T22:19:21.769439Z",
     "iopub.status.idle": "2023-02-14T22:19:21.783063Z",
     "shell.execute_reply": "2023-02-14T22:19:21.780891Z"
    },
    "id": "IDEXROQpIZtV",
    "outputId": "8afcd698-359e-40a2-b13a-8dd68697cbc1",
    "papermill": {
     "duration": 0.057866,
     "end_time": "2023-02-14T22:19:21.787315",
     "exception": false,
     "start_time": "2023-02-14T22:19:21.729449",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "1.0\n"
     ]
    }
   ],
   "source": [
    "print(accuracy_score(y_train, y_pred_train))\n",
    "print(accuracy_score(y_test, y_pred_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "0286c7eb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:19:21.868787Z",
     "iopub.status.busy": "2023-02-14T22:19:21.867500Z",
     "iopub.status.idle": "2023-02-14T22:19:22.127877Z",
     "shell.execute_reply": "2023-02-14T22:19:22.126299Z"
    },
    "papermill": {
     "duration": 0.302498,
     "end_time": "2023-02-14T22:19:22.130594",
     "exception": false,
     "start_time": "2023-02-14T22:19:21.828096",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 500x500 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 600x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#confusion matrix\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
    "cm = confusion_matrix(y_test, y_pred_test, labels=gridRF.classes_)\n",
    "disp = ConfusionMatrixDisplay(confusion_matrix=cm,display_labels=gridRF.classes_)\n",
    "fig = plt.figure(figsize=(5, 5))\n",
    "disp.plot(cmap=plt.cm.Blues) \n",
    "plt.grid(which='major')     #remove cell gridlines\n",
    "plt.gcf().set_size_inches(6, 6)   # Adjust the size of the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "741de432",
   "metadata": {
    "papermill": {
     "duration": 0.038932,
     "end_time": "2023-02-14T22:19:22.208533",
     "exception": false,
     "start_time": "2023-02-14T22:19:22.169601",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Final result table**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "3183898e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-02-14T22:19:22.289019Z",
     "iopub.status.busy": "2023-02-14T22:19:22.288559Z",
     "iopub.status.idle": "2023-02-14T22:19:22.352233Z",
     "shell.execute_reply": "2023-02-14T22:19:22.350826Z"
    },
    "papermill": {
     "duration": 0.106652,
     "end_time": "2023-02-14T22:19:22.354934",
     "exception": false,
     "start_time": "2023-02-14T22:19:22.248282",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_64eca_row0_col0, #T_64eca_row0_col1, #T_64eca_row0_col2, #T_64eca_row0_col3, #T_64eca_row0_col4, #T_64eca_row0_col5, #T_64eca_row1_col3, #T_64eca_row2_col3 {\n",
       "  background-color: #ff0000;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_64eca_row1_col0, #T_64eca_row1_col1, #T_64eca_row1_col2, #T_64eca_row1_col4, #T_64eca_row1_col5, #T_64eca_row2_col0, #T_64eca_row2_col1, #T_64eca_row2_col2, #T_64eca_row2_col4, #T_64eca_row2_col5 {\n",
       "  background-color: #008000;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_64eca_\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th class=\"col_heading level0 col0\" >accuracy</th>\n",
       "      <th class=\"col_heading level0 col1\" >f1_score</th>\n",
       "      <th class=\"col_heading level0 col2\" >precision</th>\n",
       "      <th class=\"col_heading level0 col3\" >recall</th>\n",
       "      <th class=\"col_heading level0 col4\" >balanced_accuracy</th>\n",
       "      <th class=\"col_heading level0 col5\" >auc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_64eca_level0_row0\" class=\"row_heading level0 row0\" >K Nearest Neighbors - Method 1</th>\n",
       "      <td id=\"T_64eca_row0_col0\" class=\"data row0 col0\" >0.999953</td>\n",
       "      <td id=\"T_64eca_row0_col1\" class=\"data row0 col1\" >0.999953</td>\n",
       "      <td id=\"T_64eca_row0_col2\" class=\"data row0 col2\" >0.999906</td>\n",
       "      <td id=\"T_64eca_row0_col3\" class=\"data row0 col3\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row0_col4\" class=\"data row0 col4\" >0.999953</td>\n",
       "      <td id=\"T_64eca_row0_col5\" class=\"data row0 col5\" >0.999953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_64eca_level0_row1\" class=\"row_heading level0 row1\" >Decision Trees - Method 2</th>\n",
       "      <td id=\"T_64eca_row1_col0\" class=\"data row1 col0\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row1_col1\" class=\"data row1 col1\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row1_col2\" class=\"data row1 col2\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row1_col3\" class=\"data row1 col3\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row1_col4\" class=\"data row1 col4\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row1_col5\" class=\"data row1 col5\" >1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_64eca_level0_row2\" class=\"row_heading level0 row2\" >Random Forest - Method 3</th>\n",
       "      <td id=\"T_64eca_row2_col0\" class=\"data row2 col0\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row2_col1\" class=\"data row2 col1\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row2_col2\" class=\"data row2 col2\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row2_col3\" class=\"data row2 col3\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row2_col4\" class=\"data row2 col4\" >1.000000</td>\n",
       "      <td id=\"T_64eca_row2_col5\" class=\"data row2 col5\" >1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7f1d4849a850>"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "resultsRF = train_evaluate_model(y_test)\n",
    "resultsRF.index = ['Random Forest - Method 3']\n",
    "results = results.append(resultsRF)\n",
    "results.style.background_gradient(cmap = sns.color_palette(\"blend:red,green\", as_cmap=True))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "423290c1",
   "metadata": {
    "papermill": {
     "duration": 0.038296,
     "end_time": "2023-02-14T22:19:22.432221",
     "exception": false,
     "start_time": "2023-02-14T22:19:22.393925",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "##  We Keep Learning  **To God be the glory**\n",
    "   "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "95ae5f85",
   "metadata": {
    "papermill": {
     "duration": 0.038609,
     "end_time": "2023-02-14T22:19:22.510630",
     "exception": false,
     "start_time": "2023-02-14T22:19:22.472021",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**Analysis by Olusola Fajobi, sholex111@gmail.com**\n",
    "\n",
    "---\n",
    "Appreciation to SAMI OR YERMIYAHU"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2eb52dd7",
   "metadata": {
    "papermill": {
     "duration": 0.039448,
     "end_time": "2023-02-14T22:19:22.589462",
     "exception": false,
     "start_time": "2023-02-14T22:19:22.550014",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.12"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 191.782961,
   "end_time": "2023-02-14T22:19:25.252061",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2023-02-14T22:16:13.469100",
   "version": "2.3.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}