{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "bf709519-f491-4f9b-b9ed-53c3869b114c",
   "metadata": {},
   "source": [
    "# Number Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "23eba203-ea09-4786-8935-65742a920b32",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "49fe9e33-847e-4184-b35b-8cf730130b7e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6      148             72             35        0  33.6   \n",
       "1            1       85             66             29        0  26.6   \n",
       "2            8      183             64              0        0  23.3   \n",
       "3            1       89             66             23       94  28.1   \n",
       "4            0      137             40             35      168  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_path = os.path.expanduser(\"../../data/diabetes.csv\")\n",
    "df = pd.read_csv(data_path)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33980054-2917-4392-9312-e53fef085d09",
   "metadata": {},
   "source": [
    "## Inspecting the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a2977276-cc8d-4088-8c6f-28ca6811a9be",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 768 entries, 0 to 767\n",
      "Data columns (total 9 columns):\n",
      " #   Column                    Non-Null Count  Dtype  \n",
      "---  ------                    --------------  -----  \n",
      " 0   Pregnancies               768 non-null    int64  \n",
      " 1   Glucose                   768 non-null    int64  \n",
      " 2   BloodPressure             768 non-null    int64  \n",
      " 3   SkinThickness             768 non-null    int64  \n",
      " 4   Insulin                   768 non-null    int64  \n",
      " 5   BMI                       768 non-null    float64\n",
      " 6   DiabetesPedigreeFunction  768 non-null    float64\n",
      " 7   Age                       768 non-null    int64  \n",
      " 8   Outcome                   768 non-null    int64  \n",
      "dtypes: float64(2), int64(7)\n",
      "memory usage: 54.1 KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "391cbf96-dcc0-4fc7-bc08-3f9402615f78",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.845052</td>\n",
       "      <td>120.894531</td>\n",
       "      <td>69.105469</td>\n",
       "      <td>20.536458</td>\n",
       "      <td>79.799479</td>\n",
       "      <td>31.992578</td>\n",
       "      <td>0.471876</td>\n",
       "      <td>33.240885</td>\n",
       "      <td>0.348958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.369578</td>\n",
       "      <td>31.972618</td>\n",
       "      <td>19.355807</td>\n",
       "      <td>15.952218</td>\n",
       "      <td>115.244002</td>\n",
       "      <td>7.884160</td>\n",
       "      <td>0.331329</td>\n",
       "      <td>11.760232</td>\n",
       "      <td>0.476951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.078000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>27.300000</td>\n",
       "      <td>0.243750</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>117.000000</td>\n",
       "      <td>72.000000</td>\n",
       "      <td>23.000000</td>\n",
       "      <td>30.500000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>0.372500</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>140.250000</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>127.250000</td>\n",
       "      <td>36.600000</td>\n",
       "      <td>0.626250</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>17.000000</td>\n",
       "      <td>199.000000</td>\n",
       "      <td>122.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>846.000000</td>\n",
       "      <td>67.100000</td>\n",
       "      <td>2.420000</td>\n",
       "      <td>81.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Pregnancies     Glucose  BloodPressure  SkinThickness     Insulin  \\\n",
       "count   768.000000  768.000000     768.000000     768.000000  768.000000   \n",
       "mean      3.845052  120.894531      69.105469      20.536458   79.799479   \n",
       "std       3.369578   31.972618      19.355807      15.952218  115.244002   \n",
       "min       0.000000    0.000000       0.000000       0.000000    0.000000   \n",
       "25%       1.000000   99.000000      62.000000       0.000000    0.000000   \n",
       "50%       3.000000  117.000000      72.000000      23.000000   30.500000   \n",
       "75%       6.000000  140.250000      80.000000      32.000000  127.250000   \n",
       "max      17.000000  199.000000     122.000000      99.000000  846.000000   \n",
       "\n",
       "              BMI  DiabetesPedigreeFunction         Age     Outcome  \n",
       "count  768.000000                768.000000  768.000000  768.000000  \n",
       "mean    31.992578                  0.471876   33.240885    0.348958  \n",
       "std      7.884160                  0.331329   11.760232    0.476951  \n",
       "min      0.000000                  0.078000   21.000000    0.000000  \n",
       "25%     27.300000                  0.243750   24.000000    0.000000  \n",
       "50%     32.000000                  0.372500   29.000000    0.000000  \n",
       "75%     36.600000                  0.626250   41.000000    1.000000  \n",
       "max     67.100000                  2.420000   81.000000    1.000000  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "854f88fe-855a-4fe8-8fb8-fc075b4d30d3",
   "metadata": {},
   "source": [
    "## Visualizing the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ebc2cb8c-8a75-4e3d-a6c9-bb65b9ea3da1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2500x2000 with 9 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.hist(bins=50, figsize=(25, 20))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5f6d42f5-1976-4db3-9952-5a149e407b63",
   "metadata": {},
   "source": [
    "## Removing duplicated data points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b301472c-3a8d-4e33-a253-b69208dd47a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop_duplicates(keep=\"first\", inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c2415b4-4041-434f-8c25-f614cfae3bec",
   "metadata": {},
   "source": [
    "## Creating training and testing set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ecc191ce-4933-460b-ad5c-0f2a60a65633",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df, test_df = train_test_split(df, test_size=0.2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf75f778-f9ed-4f28-a357-9ed5e035c55b",
   "metadata": {},
   "source": [
    "## Gaining further insight"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3ad46965-615c-4d08-84de-76d0902138d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Pregnancies</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.135109</td>\n",
       "      <td>0.164122</td>\n",
       "      <td>-0.041149</td>\n",
       "      <td>-0.056988</td>\n",
       "      <td>0.017513</td>\n",
       "      <td>-0.015260</td>\n",
       "      <td>0.537494</td>\n",
       "      <td>0.217668</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Glucose</th>\n",
       "      <td>0.135109</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.164170</td>\n",
       "      <td>0.048504</td>\n",
       "      <td>0.328315</td>\n",
       "      <td>0.210757</td>\n",
       "      <td>0.125436</td>\n",
       "      <td>0.269642</td>\n",
       "      <td>0.475968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BloodPressure</th>\n",
       "      <td>0.164122</td>\n",
       "      <td>0.164170</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.214924</td>\n",
       "      <td>0.080210</td>\n",
       "      <td>0.249102</td>\n",
       "      <td>0.044764</td>\n",
       "      <td>0.241728</td>\n",
       "      <td>0.114867</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SkinThickness</th>\n",
       "      <td>-0.041149</td>\n",
       "      <td>0.048504</td>\n",
       "      <td>0.214924</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.424873</td>\n",
       "      <td>0.391442</td>\n",
       "      <td>0.176407</td>\n",
       "      <td>-0.088288</td>\n",
       "      <td>0.097148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Insulin</th>\n",
       "      <td>-0.056988</td>\n",
       "      <td>0.328315</td>\n",
       "      <td>0.080210</td>\n",
       "      <td>0.424873</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.193953</td>\n",
       "      <td>0.140380</td>\n",
       "      <td>-0.034457</td>\n",
       "      <td>0.140022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>0.017513</td>\n",
       "      <td>0.210757</td>\n",
       "      <td>0.249102</td>\n",
       "      <td>0.391442</td>\n",
       "      <td>0.193953</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.126622</td>\n",
       "      <td>0.020420</td>\n",
       "      <td>0.306521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <td>-0.015260</td>\n",
       "      <td>0.125436</td>\n",
       "      <td>0.044764</td>\n",
       "      <td>0.176407</td>\n",
       "      <td>0.140380</td>\n",
       "      <td>0.126622</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.051460</td>\n",
       "      <td>0.170353</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>0.537494</td>\n",
       "      <td>0.269642</td>\n",
       "      <td>0.241728</td>\n",
       "      <td>-0.088288</td>\n",
       "      <td>-0.034457</td>\n",
       "      <td>0.020420</td>\n",
       "      <td>0.051460</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.234581</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Outcome</th>\n",
       "      <td>0.217668</td>\n",
       "      <td>0.475968</td>\n",
       "      <td>0.114867</td>\n",
       "      <td>0.097148</td>\n",
       "      <td>0.140022</td>\n",
       "      <td>0.306521</td>\n",
       "      <td>0.170353</td>\n",
       "      <td>0.234581</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          Pregnancies   Glucose  BloodPressure  SkinThickness  \\\n",
       "Pregnancies                  1.000000  0.135109       0.164122      -0.041149   \n",
       "Glucose                      0.135109  1.000000       0.164170       0.048504   \n",
       "BloodPressure                0.164122  0.164170       1.000000       0.214924   \n",
       "SkinThickness               -0.041149  0.048504       0.214924       1.000000   \n",
       "Insulin                     -0.056988  0.328315       0.080210       0.424873   \n",
       "BMI                          0.017513  0.210757       0.249102       0.391442   \n",
       "DiabetesPedigreeFunction    -0.015260  0.125436       0.044764       0.176407   \n",
       "Age                          0.537494  0.269642       0.241728      -0.088288   \n",
       "Outcome                      0.217668  0.475968       0.114867       0.097148   \n",
       "\n",
       "                           Insulin       BMI  DiabetesPedigreeFunction  \\\n",
       "Pregnancies              -0.056988  0.017513                 -0.015260   \n",
       "Glucose                   0.328315  0.210757                  0.125436   \n",
       "BloodPressure             0.080210  0.249102                  0.044764   \n",
       "SkinThickness             0.424873  0.391442                  0.176407   \n",
       "Insulin                   1.000000  0.193953                  0.140380   \n",
       "BMI                       0.193953  1.000000                  0.126622   \n",
       "DiabetesPedigreeFunction  0.140380  0.126622                  1.000000   \n",
       "Age                      -0.034457  0.020420                  0.051460   \n",
       "Outcome                   0.140022  0.306521                  0.170353   \n",
       "\n",
       "                               Age   Outcome  \n",
       "Pregnancies               0.537494  0.217668  \n",
       "Glucose                   0.269642  0.475968  \n",
       "BloodPressure             0.241728  0.114867  \n",
       "SkinThickness            -0.088288  0.097148  \n",
       "Insulin                  -0.034457  0.140022  \n",
       "BMI                       0.020420  0.306521  \n",
       "DiabetesPedigreeFunction  0.051460  0.170353  \n",
       "Age                       1.000000  0.234581  \n",
       "Outcome                   0.234581  1.000000  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "correlation_matrix = train_df.corr(method=\"pearson\")\n",
    "correlation_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "e2faef62-4795-4963-a011-66cac38465a0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SkinThickness               0.097148\n",
       "BloodPressure               0.114867\n",
       "Insulin                     0.140022\n",
       "DiabetesPedigreeFunction    0.170353\n",
       "Pregnancies                 0.217668\n",
       "Age                         0.234581\n",
       "BMI                         0.306521\n",
       "Glucose                     0.475968\n",
       "Outcome                     1.000000\n",
       "Name: Outcome, dtype: float64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "correlation_matrix[\"Outcome\"].sort_values()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d750195-c1f1-4c6b-8415-871aafab4218",
   "metadata": {},
   "source": [
    "## Handling missing data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "a7cd2214-4e2d-4609-bf8c-d1c81b212250",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/7w/fv5n0x414253d7dv5g2wwmb40000gn/T/ipykernel_1701/551462321.py:4: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
      "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
      "\n",
      "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
      "\n",
      "\n",
      "  train_df[name].replace(0, np.nan, inplace=True)\n"
     ]
    }
   ],
   "source": [
    "names = [\n",
    "    \"Glucose\",\n",
    "    \"BloodPressure\",\n",
    "    \"SkinThickness\",\n",
    "    \"Insulin\",\n",
    "    \"BMI\",\n",
    "    \"DiabetesPedigreeFunction\",\n",
    "    \"Age\",\n",
    "]\n",
    "\n",
    "for name in names:\n",
    "    train_df[name].replace(0, np.nan, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "9fae1487-4f92-4802-9df0-afd8fd67349f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>4</td>\n",
       "      <td>125.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>32.3</td>\n",
       "      <td>0.536</td>\n",
       "      <td>27</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>394</th>\n",
       "      <td>4</td>\n",
       "      <td>158.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>32.9</td>\n",
       "      <td>0.803</td>\n",
       "      <td>31</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>3</td>\n",
       "      <td>111.0</td>\n",
       "      <td>62.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>22.6</td>\n",
       "      <td>0.142</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>274</th>\n",
       "      <td>13</td>\n",
       "      <td>106.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>34.2</td>\n",
       "      <td>0.251</td>\n",
       "      <td>52</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>285.0</td>\n",
       "      <td>44.2</td>\n",
       "      <td>0.167</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "683            4    125.0           80.0            NaN      NaN  32.3   \n",
       "394            4    158.0           78.0            NaN      NaN  32.9   \n",
       "190            3    111.0           62.0            NaN      NaN  22.6   \n",
       "274           13    106.0           70.0            NaN      NaN  34.2   \n",
       "162            0    114.0           80.0           34.0    285.0  44.2   \n",
       "\n",
       "     DiabetesPedigreeFunction  Age  Outcome  \n",
       "683                     0.536   27        1  \n",
       "394                     0.803   31        1  \n",
       "190                     0.142   21        0  \n",
       "274                     0.251   52        0  \n",
       "162                     0.167   27        0  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "7542d555-810d-4811-bf5b-010c4ce4471d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/7w/fv5n0x414253d7dv5g2wwmb40000gn/T/ipykernel_1701/2039840509.py:13: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
      "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
      "\n",
      "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
      "\n",
      "\n",
      "  train_df[\"BMI\"].fillna(bmi_median, inplace=True)\n",
      "/var/folders/7w/fv5n0x414253d7dv5g2wwmb40000gn/T/ipykernel_1701/2039840509.py:14: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
      "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
      "\n",
      "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
      "\n",
      "\n",
      "  train_df[\"Age\"].fillna(age_median, inplace=True)\n",
      "/var/folders/7w/fv5n0x414253d7dv5g2wwmb40000gn/T/ipykernel_1701/2039840509.py:15: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
      "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
      "\n",
      "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
      "\n",
      "\n",
      "  train_df[\"DiabetesPedigreeFunction\"].fillna(dpf_median, inplace=True)\n"
     ]
    }
   ],
   "source": [
    "glucose_median = train_df[\"Glucose\"].median()\n",
    "blood_pressure_median = train_df[\"BloodPressure\"].median()\n",
    "skin_thickness_median = train_df[\"SkinThickness\"].median()\n",
    "insulin_median = train_df[\"Insulin\"].median()\n",
    "bmi_median = train_df[\"BMI\"].median()\n",
    "age_median = train_df[\"Age\"].median()\n",
    "dpf_median = train_df[\"DiabetesPedigreeFunction\"].median()\n",
    "\n",
    "train_df[\"Glucose\"].fillna(glucose_median, inplace=True)\n",
    "train_df[\"BloodPressure\"].fillna(blood_pressure_median, inplace=True)\n",
    "train_df[\"SkinThickness\"].fillna(skin_thickness_median, inplace=True)\n",
    "train_df[\"Insulin\"].fillna(insulin_median, inplace=True)\n",
    "train_df[\"BMI\"].fillna(bmi_median, inplace=True)\n",
    "train_df[\"Age\"].fillna(age_median, inplace=True)\n",
    "train_df[\"DiabetesPedigreeFunction\"].fillna(dpf_median, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "51d1257e-be6e-48a2-9927-70f50635015d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>4</td>\n",
       "      <td>125.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>32.3</td>\n",
       "      <td>0.536</td>\n",
       "      <td>27</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>394</th>\n",
       "      <td>4</td>\n",
       "      <td>158.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>32.9</td>\n",
       "      <td>0.803</td>\n",
       "      <td>31</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>3</td>\n",
       "      <td>111.0</td>\n",
       "      <td>62.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>22.6</td>\n",
       "      <td>0.142</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>274</th>\n",
       "      <td>13</td>\n",
       "      <td>106.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>34.2</td>\n",
       "      <td>0.251</td>\n",
       "      <td>52</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>285.0</td>\n",
       "      <td>44.2</td>\n",
       "      <td>0.167</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "683            4    125.0           80.0           29.0    125.0  32.3   \n",
       "394            4    158.0           78.0           29.0    125.0  32.9   \n",
       "190            3    111.0           62.0           29.0    125.0  22.6   \n",
       "274           13    106.0           70.0           29.0    125.0  34.2   \n",
       "162            0    114.0           80.0           34.0    285.0  44.2   \n",
       "\n",
       "     DiabetesPedigreeFunction  Age  Outcome  \n",
       "683                     0.536   27        1  \n",
       "394                     0.803   31        1  \n",
       "190                     0.142   21        0  \n",
       "274                     0.251   52        0  \n",
       "162                     0.167   27        0  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ffaa8cf2-5956-4c16-95ce-6f03ebd941d5",
   "metadata": {},
   "source": [
    "## Encoding categorial attributes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "f96db2cd-7241-4d41-bdbf-291cd4d7b1f6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "      <th>fitness</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>4</td>\n",
       "      <td>125.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>32.3</td>\n",
       "      <td>0.536</td>\n",
       "      <td>27</td>\n",
       "      <td>1</td>\n",
       "      <td>very good</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>394</th>\n",
       "      <td>4</td>\n",
       "      <td>158.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>32.9</td>\n",
       "      <td>0.803</td>\n",
       "      <td>31</td>\n",
       "      <td>1</td>\n",
       "      <td>very good</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>3</td>\n",
       "      <td>111.0</td>\n",
       "      <td>62.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>22.6</td>\n",
       "      <td>0.142</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>bad</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>274</th>\n",
       "      <td>13</td>\n",
       "      <td>106.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>34.2</td>\n",
       "      <td>0.251</td>\n",
       "      <td>52</td>\n",
       "      <td>0</td>\n",
       "      <td>moderate</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>285.0</td>\n",
       "      <td>44.2</td>\n",
       "      <td>0.167</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>very good</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "683            4    125.0           80.0           29.0    125.0  32.3   \n",
       "394            4    158.0           78.0           29.0    125.0  32.9   \n",
       "190            3    111.0           62.0           29.0    125.0  22.6   \n",
       "274           13    106.0           70.0           29.0    125.0  34.2   \n",
       "162            0    114.0           80.0           34.0    285.0  44.2   \n",
       "\n",
       "     DiabetesPedigreeFunction  Age  Outcome    fitness  \n",
       "683                     0.536   27        1  very good  \n",
       "394                     0.803   31        1  very good  \n",
       "190                     0.142   21        0        bad  \n",
       "274                     0.251   52        0   moderate  \n",
       "162                     0.167   27        0  very good  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Copy original dataframe and add new column with random fitness values\n",
    "temp_df = train_df.copy()\n",
    "fitness_values = [\n",
    "    \"bad\",\n",
    "    \"moderate\",\n",
    "    \"good\",\n",
    "    \"very good\",\n",
    "]\n",
    "temp_df[\"fitness\"] = np.random.choice(fitness_values, temp_df.shape[0])\n",
    "\n",
    "temp_df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "ce5946b5-30a3-4628-afb9-68190fe37792",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class id 0 has label bad\n",
      "class id 1 has label good\n",
      "class id 2 has label moderate\n",
      "class id 3 has label very good\n",
      "\n",
      "Encoded fitness values for first 10 entries: [3 3 0 2 3 0 1 3 2 1]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "encoder = LabelEncoder()\n",
    "fitness_encoded = encoder.fit_transform(temp_df[\"fitness\"])\n",
    "\n",
    "for id_, class_ in enumerate(encoder.classes_):\n",
    "    print(f\"class id {id_} has label {class_}\")\n",
    "\n",
    "print()\n",
    "print(f\"Encoded fitness values for first 10 entries: {fitness_encoded[:10]}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e91b169e-4532-414f-a4d6-37cb9539bfb7",
   "metadata": {},
   "source": [
    "## Rescaling or standardizing attributes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "e5958be0-dd02-41c8-9cac-4ffe8a40a2ea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.470588</td>\n",
       "      <td>0.896774</td>\n",
       "      <td>0.444444</td>\n",
       "      <td>0.239130</td>\n",
       "      <td>0.133413</td>\n",
       "      <td>0.104294</td>\n",
       "      <td>0.253629</td>\n",
       "      <td>0.183333</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.058824</td>\n",
       "      <td>0.290323</td>\n",
       "      <td>0.466667</td>\n",
       "      <td>0.173913</td>\n",
       "      <td>0.096154</td>\n",
       "      <td>0.202454</td>\n",
       "      <td>0.038002</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.294118</td>\n",
       "      <td>0.464516</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.239130</td>\n",
       "      <td>0.133413</td>\n",
       "      <td>0.151329</td>\n",
       "      <td>0.052519</td>\n",
       "      <td>0.150000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.176471</td>\n",
       "      <td>0.219355</td>\n",
       "      <td>0.288889</td>\n",
       "      <td>0.271739</td>\n",
       "      <td>0.088942</td>\n",
       "      <td>0.261759</td>\n",
       "      <td>0.072588</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.588235</td>\n",
       "      <td>0.458065</td>\n",
       "      <td>0.533333</td>\n",
       "      <td>0.239130</td>\n",
       "      <td>0.133413</td>\n",
       "      <td>0.349693</td>\n",
       "      <td>0.023911</td>\n",
       "      <td>0.133333</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies   Glucose  BloodPressure  SkinThickness   Insulin       BMI  \\\n",
       "2     0.470588  0.896774       0.444444       0.239130  0.133413  0.104294   \n",
       "3     0.058824  0.290323       0.466667       0.173913  0.096154  0.202454   \n",
       "5     0.294118  0.464516       0.555556       0.239130  0.133413  0.151329   \n",
       "6     0.176471  0.219355       0.288889       0.271739  0.088942  0.261759   \n",
       "7     0.588235  0.458065       0.533333       0.239130  0.133413  0.349693   \n",
       "\n",
       "   DiabetesPedigreeFunction       Age  Outcome  \n",
       "2                  0.253629  0.183333      1.0  \n",
       "3                  0.038002  0.000000      0.0  \n",
       "5                  0.052519  0.150000      0.0  \n",
       "6                  0.072588  0.083333      1.0  \n",
       "7                  0.023911  0.133333      0.0  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "# initialize min-max scaler\n",
    "mm_scaler = MinMaxScaler()\n",
    "\n",
    "temp1_df = train_df.copy()\n",
    "column_names = temp1_df.columns.tolist()\n",
    "\n",
    "# transform all attributes\n",
    "temp1_df[column_names] = mm_scaler.fit_transform(temp1_df[column_names])\n",
    "\n",
    "temp1_df.sort_index(inplace=True)\n",
    "temp1_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "b6c101ee-c8d5-4fbc-9982-cb6e711c6bc6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.470588</td>\n",
       "      <td>0.896774</td>\n",
       "      <td>0.444444</td>\n",
       "      <td>0.239130</td>\n",
       "      <td>0.133413</td>\n",
       "      <td>0.104294</td>\n",
       "      <td>0.253629</td>\n",
       "      <td>0.183333</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.058824</td>\n",
       "      <td>0.290323</td>\n",
       "      <td>0.466667</td>\n",
       "      <td>0.173913</td>\n",
       "      <td>0.096154</td>\n",
       "      <td>0.202454</td>\n",
       "      <td>0.038002</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.294118</td>\n",
       "      <td>0.464516</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.239130</td>\n",
       "      <td>0.133413</td>\n",
       "      <td>0.151329</td>\n",
       "      <td>0.052519</td>\n",
       "      <td>0.150000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.176471</td>\n",
       "      <td>0.219355</td>\n",
       "      <td>0.288889</td>\n",
       "      <td>0.271739</td>\n",
       "      <td>0.088942</td>\n",
       "      <td>0.261759</td>\n",
       "      <td>0.072588</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.588235</td>\n",
       "      <td>0.458065</td>\n",
       "      <td>0.533333</td>\n",
       "      <td>0.239130</td>\n",
       "      <td>0.133413</td>\n",
       "      <td>0.349693</td>\n",
       "      <td>0.023911</td>\n",
       "      <td>0.133333</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies   Glucose  BloodPressure  SkinThickness   Insulin       BMI  \\\n",
       "2     0.470588  0.896774       0.444444       0.239130  0.133413  0.104294   \n",
       "3     0.058824  0.290323       0.466667       0.173913  0.096154  0.202454   \n",
       "5     0.294118  0.464516       0.555556       0.239130  0.133413  0.151329   \n",
       "6     0.176471  0.219355       0.288889       0.271739  0.088942  0.261759   \n",
       "7     0.588235  0.458065       0.533333       0.239130  0.133413  0.349693   \n",
       "\n",
       "   DiabetesPedigreeFunction       Age  Outcome  \n",
       "2                  0.253629  0.183333      1.0  \n",
       "3                  0.038002  0.000000      0.0  \n",
       "5                  0.052519  0.150000      0.0  \n",
       "6                  0.072588  0.083333      1.0  \n",
       "7                  0.023911  0.133333      0.0  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "standard_scaler = StandardScaler()\n",
    "\n",
    "temp2_df = train_df.copy()\n",
    "\n",
    "# transform all attributes\n",
    "temp2_df[column_names] = mm_scaler.fit_transform(temp2_df[column_names])\n",
    "temp2_df.sort_index(inplace=True)\n",
    "temp2_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8a34d793-33f6-477d-bf01-01a331d9e0d7",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}