{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "CC - Module Python pour le Machine Learning Bekombo IABD B3 Soir"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pycaret as py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Store</th>\n",
       "      <th>Date</th>\n",
       "      <th>Daily_Sales</th>\n",
       "      <th>Holiday_Flag</th>\n",
       "      <th>Temperature</th>\n",
       "      <th>Fuel_Price</th>\n",
       "      <th>CPI</th>\n",
       "      <th>Unemployment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-05-02</td>\n",
       "      <td>1643690.90</td>\n",
       "      <td>0</td>\n",
       "      <td>42.31</td>\n",
       "      <td>2.572</td>\n",
       "      <td>211.096358</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-12-02</td>\n",
       "      <td>1641957.44</td>\n",
       "      <td>1</td>\n",
       "      <td>38.51</td>\n",
       "      <td>2.548</td>\n",
       "      <td>211.242170</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-02-19</td>\n",
       "      <td>1611968.17</td>\n",
       "      <td>0</td>\n",
       "      <td>39.93</td>\n",
       "      <td>2.514</td>\n",
       "      <td>211.289143</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-02-26</td>\n",
       "      <td>1409727.59</td>\n",
       "      <td>0</td>\n",
       "      <td>46.63</td>\n",
       "      <td>2.561</td>\n",
       "      <td>211.319643</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-05-03</td>\n",
       "      <td>1554806.68</td>\n",
       "      <td>0</td>\n",
       "      <td>46.50</td>\n",
       "      <td>2.625</td>\n",
       "      <td>211.350143</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Store        Date  Daily_Sales  Holiday_Flag  Temperature  Fuel_Price  \\\n",
       "0      1  2010-05-02   1643690.90             0        42.31       2.572   \n",
       "1      1  2010-12-02   1641957.44             1        38.51       2.548   \n",
       "2      1  2010-02-19   1611968.17             0        39.93       2.514   \n",
       "3      1  2010-02-26   1409727.59             0        46.63       2.561   \n",
       "4      1  2010-05-03   1554806.68             0        46.50       2.625   \n",
       "\n",
       "          CPI  Unemployment  \n",
       "0  211.096358         8.106  \n",
       "1  211.242170         8.106  \n",
       "2  211.289143         8.106  \n",
       "3  211.319643         8.106  \n",
       "4  211.350143         8.106  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv(\"./datasets/Walmart.csv\")\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store           0\n",
       "Date            0\n",
       "Daily_Sales     0\n",
       "Holiday_Flag    0\n",
       "Temperature     0\n",
       "Fuel_Price      0\n",
       "CPI             0\n",
       "Unemployment    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False    6435\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "duplicates = data.duplicated()\n",
    "duplicates.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store             int64\n",
       "Date             object\n",
       "Daily_Sales     float64\n",
       "Holiday_Flag      int64\n",
       "Temperature     float64\n",
       "Fuel_Price      float64\n",
       "CPI             float64\n",
       "Unemployment    float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 6435 entries, 0 to 6434\n",
      "Data columns (total 8 columns):\n",
      " #   Column        Non-Null Count  Dtype  \n",
      "---  ------        --------------  -----  \n",
      " 0   Store         6435 non-null   int64  \n",
      " 1   Date          6435 non-null   object \n",
      " 2   Daily_Sales   6435 non-null   float64\n",
      " 3   Holiday_Flag  6435 non-null   int64  \n",
      " 4   Temperature   6435 non-null   float64\n",
      " 5   Fuel_Price    6435 non-null   float64\n",
      " 6   CPI           6435 non-null   float64\n",
      " 7   Unemployment  6435 non-null   float64\n",
      "dtypes: float64(5), int64(2), object(1)\n",
      "memory usage: 402.3+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
       "       18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34,\n",
       "       35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45], dtype=int64)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.Store.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "#data['Date'] = pd.to_datetime(data['Date'])\n",
    "#data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 6435 entries, 0 to 6434\n",
      "Data columns (total 8 columns):\n",
      " #   Column        Non-Null Count  Dtype  \n",
      "---  ------        --------------  -----  \n",
      " 0   Store         6435 non-null   int64  \n",
      " 1   Date          6435 non-null   object \n",
      " 2   Daily_Sales   6435 non-null   float64\n",
      " 3   Holiday_Flag  6435 non-null   int64  \n",
      " 4   Temperature   6435 non-null   float64\n",
      " 5   Fuel_Price    6435 non-null   float64\n",
      " 6   CPI           6435 non-null   float64\n",
      " 7   Unemployment  6435 non-null   float64\n",
      "dtypes: float64(5), int64(2), object(1)\n",
      "memory usage: 402.3+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>Store</th>\n",
       "      <th>Date</th>\n",
       "      <th>Daily_Sales</th>\n",
       "      <th>Holiday_Flag</th>\n",
       "      <th>Temperature</th>\n",
       "      <th>Fuel_Price</th>\n",
       "      <th>CPI</th>\n",
       "      <th>Unemployment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-05-02</td>\n",
       "      <td>1643690.90</td>\n",
       "      <td>0</td>\n",
       "      <td>42.31</td>\n",
       "      <td>2.572</td>\n",
       "      <td>211.096358</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-12-02</td>\n",
       "      <td>1641957.44</td>\n",
       "      <td>1</td>\n",
       "      <td>38.51</td>\n",
       "      <td>2.548</td>\n",
       "      <td>211.242170</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-02-19</td>\n",
       "      <td>1611968.17</td>\n",
       "      <td>0</td>\n",
       "      <td>39.93</td>\n",
       "      <td>2.514</td>\n",
       "      <td>211.289143</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-02-26</td>\n",
       "      <td>1409727.59</td>\n",
       "      <td>0</td>\n",
       "      <td>46.63</td>\n",
       "      <td>2.561</td>\n",
       "      <td>211.319643</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-05-03</td>\n",
       "      <td>1554806.68</td>\n",
       "      <td>0</td>\n",
       "      <td>46.50</td>\n",
       "      <td>2.625</td>\n",
       "      <td>211.350143</td>\n",
       "      <td>8.106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6430</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-09-28</td>\n",
       "      <td>713173.95</td>\n",
       "      <td>0</td>\n",
       "      <td>64.88</td>\n",
       "      <td>3.997</td>\n",
       "      <td>192.013558</td>\n",
       "      <td>8.684</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6431</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-05-10</td>\n",
       "      <td>733455.07</td>\n",
       "      <td>0</td>\n",
       "      <td>64.89</td>\n",
       "      <td>3.985</td>\n",
       "      <td>192.170412</td>\n",
       "      <td>8.667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6432</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-12-10</td>\n",
       "      <td>734464.36</td>\n",
       "      <td>0</td>\n",
       "      <td>54.47</td>\n",
       "      <td>4.000</td>\n",
       "      <td>192.327265</td>\n",
       "      <td>8.667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6433</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-10-19</td>\n",
       "      <td>718125.53</td>\n",
       "      <td>0</td>\n",
       "      <td>56.47</td>\n",
       "      <td>3.969</td>\n",
       "      <td>192.330854</td>\n",
       "      <td>8.667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6434</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-10-26</td>\n",
       "      <td>760281.43</td>\n",
       "      <td>0</td>\n",
       "      <td>58.85</td>\n",
       "      <td>3.882</td>\n",
       "      <td>192.308899</td>\n",
       "      <td>8.667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6435 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Store        Date  Daily_Sales  Holiday_Flag  Temperature  Fuel_Price  \\\n",
       "0         1  2010-05-02   1643690.90             0        42.31       2.572   \n",
       "1         1  2010-12-02   1641957.44             1        38.51       2.548   \n",
       "2         1  2010-02-19   1611968.17             0        39.93       2.514   \n",
       "3         1  2010-02-26   1409727.59             0        46.63       2.561   \n",
       "4         1  2010-05-03   1554806.68             0        46.50       2.625   \n",
       "...     ...         ...          ...           ...          ...         ...   \n",
       "6430     45  2012-09-28    713173.95             0        64.88       3.997   \n",
       "6431     45  2012-05-10    733455.07             0        64.89       3.985   \n",
       "6432     45  2012-12-10    734464.36             0        54.47       4.000   \n",
       "6433     45  2012-10-19    718125.53             0        56.47       3.969   \n",
       "6434     45  2012-10-26    760281.43             0        58.85       3.882   \n",
       "\n",
       "             CPI  Unemployment  \n",
       "0     211.096358         8.106  \n",
       "1     211.242170         8.106  \n",
       "2     211.289143         8.106  \n",
       "3     211.319643         8.106  \n",
       "4     211.350143         8.106  \n",
       "...          ...           ...  \n",
       "6430  192.013558         8.684  \n",
       "6431  192.170412         8.667  \n",
       "6432  192.327265         8.667  \n",
       "6433  192.330854         8.667  \n",
       "6434  192.308899         8.667  \n",
       "\n",
       "[6435 rows x 8 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>Store</th>\n",
       "      <th>Daily_Sales</th>\n",
       "      <th>Holiday_Flag</th>\n",
       "      <th>Temperature</th>\n",
       "      <th>Fuel_Price</th>\n",
       "      <th>CPI</th>\n",
       "      <th>Unemployment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>6435.000000</td>\n",
       "      <td>6.435000e+03</td>\n",
       "      <td>6435.000000</td>\n",
       "      <td>6435.000000</td>\n",
       "      <td>6435.000000</td>\n",
       "      <td>6435.000000</td>\n",
       "      <td>6435.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>23.000000</td>\n",
       "      <td>1.046965e+06</td>\n",
       "      <td>0.069930</td>\n",
       "      <td>60.663782</td>\n",
       "      <td>3.358607</td>\n",
       "      <td>171.578394</td>\n",
       "      <td>7.999151</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>12.988182</td>\n",
       "      <td>5.643666e+05</td>\n",
       "      <td>0.255049</td>\n",
       "      <td>18.444933</td>\n",
       "      <td>0.459020</td>\n",
       "      <td>39.356712</td>\n",
       "      <td>1.875885</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.099862e+05</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-2.060000</td>\n",
       "      <td>2.472000</td>\n",
       "      <td>126.064000</td>\n",
       "      <td>3.879000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>12.000000</td>\n",
       "      <td>5.533501e+05</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>47.460000</td>\n",
       "      <td>2.933000</td>\n",
       "      <td>131.735000</td>\n",
       "      <td>6.891000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>23.000000</td>\n",
       "      <td>9.607460e+05</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>62.670000</td>\n",
       "      <td>3.445000</td>\n",
       "      <td>182.616521</td>\n",
       "      <td>7.874000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>34.000000</td>\n",
       "      <td>1.420159e+06</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>74.940000</td>\n",
       "      <td>3.735000</td>\n",
       "      <td>212.743293</td>\n",
       "      <td>8.622000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>45.000000</td>\n",
       "      <td>3.818686e+06</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>100.140000</td>\n",
       "      <td>4.468000</td>\n",
       "      <td>227.232807</td>\n",
       "      <td>14.313000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Store   Daily_Sales  Holiday_Flag  Temperature   Fuel_Price  \\\n",
       "count  6435.000000  6.435000e+03   6435.000000  6435.000000  6435.000000   \n",
       "mean     23.000000  1.046965e+06      0.069930    60.663782     3.358607   \n",
       "std      12.988182  5.643666e+05      0.255049    18.444933     0.459020   \n",
       "min       1.000000  2.099862e+05      0.000000    -2.060000     2.472000   \n",
       "25%      12.000000  5.533501e+05      0.000000    47.460000     2.933000   \n",
       "50%      23.000000  9.607460e+05      0.000000    62.670000     3.445000   \n",
       "75%      34.000000  1.420159e+06      0.000000    74.940000     3.735000   \n",
       "max      45.000000  3.818686e+06      1.000000   100.140000     4.468000   \n",
       "\n",
       "               CPI  Unemployment  \n",
       "count  6435.000000   6435.000000  \n",
       "mean    171.578394      7.999151  \n",
       "std      39.356712      1.875885  \n",
       "min     126.064000      3.879000  \n",
       "25%     131.735000      6.891000  \n",
       "50%     182.616521      7.874000  \n",
       "75%     212.743293      8.622000  \n",
       "max     227.232807     14.313000  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "#df = data.rename(columns={'Weekly_Sales': 'Daily_Sales'})\n",
    "\n",
    "#csv_data = df.to_csv(index=False)\n",
    "#with open('Walmart.csv', 'w') as f:\n",
    "    #f.write(csv_data)\n",
    "#df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = data.drop(columns={'Daily_Sales'}, axis=1)\n",
    "csv_data = df.to_csv(index=False)\n",
    "with open('./datasets/test_Walmart.csv', 'w') as f:\n",
    "    f.write(csv_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Outliers checking"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Store'>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=data, x=data.Store)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Daily_Sales'>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=data, x=data.Daily_Sales)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Daily_Sales'>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Identifier les outliers avec la méthode IQR\n",
    "Q1 = data['Daily_Sales'].quantile(0.25)\n",
    "Q3 = data['Daily_Sales'].quantile(0.75)\n",
    "IQR = Q3 - Q1\n",
    "IQR\n",
    "\n",
    "k = 1.5  # Facteur de seuil pour définir les outliers\n",
    "lower_limit = Q1 - k * IQR\n",
    "upper_limit = Q3 + k * IQR\n",
    "\n",
    "\n",
    "outliers = data[(data['Daily_Sales'] < lower_limit) | (data['Daily_Sales'] > upper_limit)]\n",
    "len(outliers)\n",
    "\n",
    "# Diviser outliers en deux\n",
    "upper_limit2 = 2800000.00\n",
    "outliers_contigus = data[(data['Daily_Sales'] > upper_limit) & (data['Daily_Sales'] <= upper_limit2)]\n",
    "outliers_non_contigus = data[data['Daily_Sales'] > upper_limit2]\n",
    "\n",
    "\n",
    "data.loc[data['Daily_Sales'] > upper_limit2, 'Daily_Sales'] = upper_limit2\n",
    "\n",
    "sns.boxplot(data=data,x=data.Daily_Sales)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Holiday_Flag'>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=data, x=data.Holiday_Flag)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Temperature'>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=data, x=data.Temperature)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Nombre d'observations considérées comme des outliers à moins 25% non-contigus :  1\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Temperature'>"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAggAAAGwCAYAAADMjZ3mAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAXu0lEQVR4nO3de5CVdf3A8c/Bhd3F5SIqIApKxggpEorjoJW/GS0hx1C7KjZYVGPhqDhmdgG8DGJWapqX0hmywmuDlhjTEAqIKaICeWFAEYUExDLiIsttn98fv/H8OH40kRbOurxeMztzzvM855wP39Puefecs26pKIoiAAC206baAwAALY9AAAASgQAAJAIBAEgEAgCQCAQAIBEIAEBSs7M3bGpqihUrVkSHDh2iVCo150wAwC5SFEWsW7cuevToEW3avPd5gp0OhBUrVkTPnj139uYAQBUtX748DjrooPfcv9OB0KFDh/IDdOzYcWfvBgDYjdauXRs9e/Ysv46/l50OhLffVujYsaNAAIAPmff7eIAPKQIAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAICkptoDAP9ZURTR2NhY7TFatKIoYtOmTRERUVtbG6VSqcoT7R51dXV7zL+V3U8gQAvX2NgYQ4cOrfYYtEBTp06N+vr6ao9BK+UtBgAgcQYBPkTWf/zMKNr4tk22bYkOC+6OiIh1A74SsVfbKg+065SatkbD/LuqPQZ7AD9p4EOkaFPTql/8msVebVv1GhXVHoA9hrcYAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASGqqPcD2iqKIxsbGiIioq6uLUqlU5YkAYPdqKa+FLeoMQmNjYwwdOjSGDh1aXhwA2JO0lNfCFhUIAEDLIBAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACCpqfYA2yuKony5sbGxipNAy1HxvbDd9wh7KD8nW73tn9eiit/zOxwImzZtik2bNpWvr127ttmH2f7+Tz/99Ga/f/jQa9oaEe2qPQXV1LS1fNHPydZv06ZN0b59+6o89g6/xTBhwoTo1KlT+atnz567ci4AoIp2+AzC97///bjooovK19euXdvskVBbW1u+fP/990ddXV2z3j98GDU2Nv7//1Ns06LeFaQatvvfgJ+TrdP23/Pbvy7ubjv806a2tnaXD1oqlcqX6+rqor6+fpc+HnzobPc9wh7Kz8k9SqmK3/N+iwEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkNdUeYHt1dXUxderU8mUA2NO0lNfCFhUIpVIp6uvrqz0GAFRNS3kt9BYDAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAASU21BwB2XKlpaxTVHqIl2rbl3S+3QqWmrdUegT2EQIAPkYb5d1V7hBavw4K7qz0CtAreYgAAEmcQoIWrq6uLqVOnVnuMFq0oiti0aVNERNTW1kapVKryRLtHXV1dtUegFRMI0MKVSqWor6+v9hgtXvv27as9ArQq3mIAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAAJKanb1hURQREbF27dpmGwYA2LXeft1++3X8vex0IKxbty4iInr27LmzdwEAVMm6deuiU6dO77m/VLxfQryHpqamWLFiRXTo0CFKpdJOD8i7W7t2bfTs2TOWL18eHTt2rPY4eyTPQXVZ/+qy/tW1K9e/KIpYt25d9OjRI9q0ee9PGuz0GYQ2bdrEQQcdtLM3Zwd17NjRN2eVeQ6qy/pXl/Wvrl21/v/pzMHbfEgRAEgEAgCQCIQWqra2NsaNGxe1tbXVHmWP5TmoLutfXda/ulrC+u/0hxQBgNbLGQQAIBEIAEAiEACARCAAAIlAqLIJEybEMcccEx06dIiuXbvGaaedFosWLao4prGxMUaNGhX77rtvNDQ0xOc///l4/fXXqzRx63X11VdHqVSKCy+8sLzN2u96r732Wpx99tmx7777Rn19ffTv3z+eeuqp8v6iKGLs2LFxwAEHRH19fZx00knx4osvVnHi1mPbtm0xZsyY6N27d9TX18ehhx4aV155ZcV/o9/6N59Zs2bFqaeeGj169IhSqRQPPPBAxf4dWes333wzhg8fHh07dozOnTvHyJEjY/369btkXoFQZTNnzoxRo0bFE088EdOmTYstW7bEZz7zmdiwYUP5mNGjR8eDDz4Y9913X8ycOTNWrFgRZ5xxRhWnbn3mzp0bv/zlL+PII4+s2G7td61//etfcfzxx0fbtm1j6tSp8cILL8TPfvaz2GeffcrHXHPNNXHDDTfErbfeGnPmzIm99947Tj755GhsbKzi5K3Dj3/847jlllviF7/4RSxcuDB+/OMfxzXXXBM33nhj+Rjr33w2bNgQAwYMiJtuuuld9+/IWg8fPjyef/75mDZtWkyZMiVmzZoV3/rWt3bNwAUtyurVq4uIKGbOnFkURVGsWbOmaNu2bXHfffeVj1m4cGEREcXjjz9erTFblXXr1hV9+vQppk2bVpxwwgnFBRdcUBSFtd8dvve97xWf+MQn3nN/U1NT0b179+InP/lJeduaNWuK2tra4q677todI7Zqp5xySvH1r3+9YtsZZ5xRDB8+vCgK678rRURx//33l6/vyFq/8MILRUQUc+fOLR8zderUolQqFa+99lqzz+gMQgvz73//OyIiunTpEhERTz/9dGzZsiVOOumk8jF9+/aNXr16xeOPP16VGVubUaNGxSmnnFKxxhHWfnf44x//GIMGDYovfvGL0bVr1xg4cGDcdttt5f1Lly6NVatWVTwHnTp1imOPPdZz0AyOO+64mD59eixevDgiIhYsWBCzZ8+OoUOHRoT13512ZK0ff/zx6Ny5cwwaNKh8zEknnRRt2rSJOXPmNPtMO/3Hmmh+TU1NceGFF8bxxx8fRxxxRERErFq1Ktq1axedO3euOLZbt26xatWqKkzZutx9993xzDPPxNy5c9M+a7/rvfzyy3HLLbfERRddFD/4wQ9i7ty5cf7550e7du1ixIgR5XXu1q1bxe08B83j0ksvjbVr10bfvn1jr732im3btsX48eNj+PDhERHWfzfakbVetWpVdO3atWJ/TU1NdOnSZZc8HwKhBRk1alQ899xzMXv27GqPskdYvnx5XHDBBTFt2rSoq6ur9jh7pKamphg0aFBcddVVERExcODAeO655+LWW2+NESNGVHm61u/ee++NSZMmxZ133hmHH354zJ8/Py688MLo0aOH9ceHFFuK8847L6ZMmRKPPPJIxZ/R7t69e2zevDnWrFlTcfzrr78e3bt3381Tti5PP/10rF69Oo466qioqamJmpqamDlzZtxwww1RU1MT3bp1s/a72AEHHBAf+9jHKrb169cvli1bFhFRXud3/uaI56B5fPe7341LL700vvKVr0T//v3jq1/9aowePTomTJgQEdZ/d9qRte7evXusXr26Yv/WrVvjzTff3CXPh0CosqIo4rzzzov7778/Hn744ejdu3fF/qOPPjratm0b06dPL29btGhRLFu2LAYPHry7x21VTjzxxHj22Wdj/vz55a9BgwbF8OHDy5et/a51/PHHp1/rXbx4cRx88MEREdG7d+/o3r17xXOwdu3amDNnjuegGbz11lvRpk3ly8Bee+0VTU1NEWH9d6cdWevBgwfHmjVr4umnny4f8/DDD0dTU1Mce+yxzT9Us3/skQ/k29/+dtGpU6dixowZxcqVK8tfb731VvmYc889t+jVq1fx8MMPF0899VQxePDgYvDgwVWcuvXa/rcYisLa72pPPvlkUVNTU4wfP7548cUXi0mTJhXt27cvfve735WPufrqq4vOnTsXf/jDH4q//e1vxbBhw4revXsXGzdurOLkrcOIESOKAw88sJgyZUqxdOnSYvLkycV+++1XXHLJJeVjrH/zWbduXTFv3rxi3rx5RUQU1157bTFv3rzi1VdfLYpix9Z6yJAhxcCBA4s5c+YUs2fPLvr06VOceeaZu2RegVBlEfGuXxMnTiwfs3HjxuI73/lOsc8++xTt27cvTj/99GLlypXVG7oVe2cgWPtd78EHHyyOOOKIora2tujbt2/xq1/9qmJ/U1NTMWbMmKJbt25FbW1tceKJJxaLFi2q0rSty9q1a4sLLrig6NWrV1FXV1d85CMfKX74wx8WmzZtKh9j/ZvPI4888q4/70eMGFEUxY6t9T//+c/izDPPLBoaGoqOHTsWX/va14p169btknn9uWcAIPEZBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQiwm5RKpf/4ddlll1V7xGZ3yCGHxPXXX1/tMYCdUFPtAWBPsXLlyvLle+65J8aOHVvxlwwbGhqqMdYHVhRFbNu2LWpqdt+Pj82bN0e7du122+MBziDAbtO9e/fyV6dOnaJUKlVsu/vuu6Nfv35RV1cXffv2jZtvvrl821deeSVKpVLce++98clPfjLq6+vjmGOOicWLF8fcuXNj0KBB0dDQEEOHDo033nijfLtzzjknTjvttLj88stj//33j44dO8a5554bmzdvLh/T1NQUEyZMiN69e0d9fX0MGDAgfv/735f3z5gxI0qlUkydOjWOPvroqK2tjdmzZ8eSJUti2LBh0a1bt2hoaIhjjjkm/vKXv5Rv9z//8z/x6quvxujRo8tnSSIiLrvssvj4xz9esTbXX399HHLIIWnu8ePHR48ePeKwww6LiIjly5fHl770pejcuXN06dIlhg0bFq+88kpzPD3AOwgEaAEmTZoUY8eOjfHjx8fChQvjqquuijFjxsQdd9xRcdy4cePiRz/6UTzzzDNRU1MTZ511VlxyySXx85//PB599NF46aWXYuzYsRW3mT59eixcuDBmzJgRd911V0yePDkuv/zy8v4JEybEb37zm7j11lvj+eefj9GjR8fZZ58dM2fOrLifSy+9NK6++upYuHBhHHnkkbF+/fr47Gc/G9OnT4958+bFkCFD4tRTT41ly5ZFRMTkyZPjoIMOiiuuuCJWrlxZcQZlR0yfPj0WLVoU06ZNiylTpsSWLVvi5JNPjg4dOsSjjz4ajz32WDQ0NMSQIUMqggdoJrvkb0QC/9HEiROLTp06la8feuihxZ133llxzJVXXlkMHjy4KIqiWLp0aRERxe23317ef9dddxURUUyfPr28bcKECcVhhx1Wvj5ixIiiS5cuxYYNG8rbbrnllqKhoaHYtm1b0djYWLRv377461//WvHYI0eOLP+N+bf/RO0DDzzwvv+uww8/vLjxxhvL1w8++ODiuuuuqzhm3LhxxYABAyq2XXfddcXBBx9cMXe3bt0q/uzwb3/72+Kwww4rmpqayts2bdpU1NfXF3/+85/fdzbgg/EZBKiyDRs2xJIlS2LkyJHxzW9+s7x969at0alTp4pjjzzyyPLlbt26RURE//79K7atXr264jYDBgyI9u3bl68PHjw41q9fH8uXL4/169fHW2+9FZ/+9KcrbrN58+YYOHBgxbZBgwZVXF+/fn1cdtll8dBDD8XKlStj69atsXHjxvIZhP9W//79Kz53sGDBgnjppZeiQ4cOFcc1NjbGkiVLmuUxgf8nEKDK1q9fHxERt912Wxx77LEV+/baa6+K623bti1ffvs9/Xdua2pq+sCP/dBDD8WBBx5Ysa+2trbi+t57711x/eKLL45p06bFT3/60/joRz8a9fX18YUvfOF9T/e3adMmiqKo2LZly5Z03Dsfb/369XH00UfHpEmT0rH777//f3xM4IMTCFBl3bp1ix49esTLL78cw4cPb/b7X7BgQWzcuDHq6+sjIuKJJ56IhoaG6NmzZ3Tp0iVqa2tj2bJlccIJJ3yg+33sscfinHPOidNPPz0i/u8F/J0fGGzXrl1s27atYtv+++8fq1atiqIoypEzf/789328o446Ku65557o2rVrdOzY8QPNCnxwPqQILcDll18eEyZMiBtuuCEWL14czz77bEycODGuvfba//q+N2/eHCNHjowXXngh/vSnP8W4cePivPPOizZt2kSHDh3i4osvjtGjR8cdd9wRS5YsiWeeeSZuvPHG9AHJd+rTp09Mnjw55s+fHwsWLIizzjornb045JBDYtasWfHaa6/FP/7xj4j4v99ueOONN+Kaa66JJUuWxE033RRTp05933/H8OHDY7/99othw4bFo48+GkuXLo0ZM2bE+eefH3//+993foGAdyUQoAX4xje+EbfffntMnDgx+vfvHyeccEL8+te/jt69e//X933iiSdGnz594lOf+lR8+ctfjs997nMV/1GmK6+8MsaMGRMTJkyIfv36xZAhQ+Khhx5638e+9tprY5999onjjjsuTj311Dj55JPjqKOOqjjmiiuuiFdeeSUOPfTQ8tsA/fr1i5tvvjluuummGDBgQDz55JNx8cUXv++/o3379jFr1qzo1atXnHHGGdGvX78YOXJkNDY2OqMAu0CpeOebgUCrcc4558SaNWvigQceqPYowIeMMwgAQCIQAIDEWwwAQOIMAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEj+FzeN8VzS12IQAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Identifier les outliers avec la méthode IQR\n",
    "Q1 = data['Temperature'].quantile(0.25)\n",
    "Q3 = data['Temperature'].quantile(0.75)\n",
    "IQR = Q3 - Q1\n",
    "\n",
    "k = 1.5  # Facteur de seuil pour définir les outliers\n",
    "lower_limit = Q1 - k * IQR\n",
    "upper_limit = Q3 + k * IQR\n",
    "\n",
    "outliers = data[(data['Temperature'] < lower_limit)]\n",
    "\n",
    "# Diviser les outliers en deux catégories\n",
    "lower_limit2 = 0\n",
    "\n",
    "outliers_below_Q1 = data[data['Temperature'] < lower_limit2]\n",
    "print(\"Nombre d'observations considérées comme des outliers à moins 25% non-contigus : \", len(outliers_below_Q1))\n",
    "\n",
    "data.loc[data['Temperature'] < lower_limit, 'Temperature'] = lower_limit\n",
    "\n",
    "sns.boxplot(data=data,x=data.Temperature)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Fuel_Price'>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=data,x=data.Fuel_Price)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='CPI'>"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAggAAAGwCAYAAADMjZ3mAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAUO0lEQVR4nO3dfWzdddn48euUbm23tZsIW1P3gARkbiDInEvRSDRkD1mmDv/gJkhESQzSQYBlMWhUgjFABHwgE2JiwITkvuOiIwPddHFjg2xDhXHDcPKgwpBtLLqMdkj3QD+/P/ztuHJtdO6mPR3n9UqadOd8z+l1rox933xPm1ZKKSUAAA7TUOsBAIDhRyAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIGk83gf29fXF9u3bo7W1NSqVyjs5EwAwSEop0dPTEx0dHdHQcPTrBMcdCNu3b49JkyYd78MBgBp6+eWXY+LEiUe9/7gDobW1tfoF2trajvdpAIAh1N3dHZMmTaqex4/muAPh0NsKbW1tAgEATjADfXuAb1IEABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAASWOtB6iFUkr09vbWegyoa6WU2LdvX0RENDU1RaVSqfFEDEfNzc3+btRIXQZCb29vzJs3r9ZjADCAlStXRktLS63HqEveYgAAkrq8gnC4veddGqWh7tcAQ+/NA9H6v/8TERE95/5XxEkjajwQw0Wl72CMefK/az1G3av7M2NpaPQPE9TaSSP8d0hVqfUARIS3GACAIxAIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAACSxloPcLhSSvT29kZERHNzc1QqlRpPBABDa7icC4fVFYTe3t6YN29ezJs3r7ocAKgnw+VcOKwCAQAYHgQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkjbUe4HCllOrnvb29g/Z1+j33YV8TgGFgiM4Fw9Xhr7nU8Bx1zIGwb9++2LdvX/XP3d3d7/gwhz//woUL3/HnP6K+gxExcmi+FgAD6ztY/XTIzgXD1L59+2LUqFE1+drH/BbDLbfcEmPHjq1+TJo0aTDnAgBq6JivINx4441xww03VP/c3d39jkdCU1NT9fPly5dHc3PzO/r8h/T29v67ShuG1bssABz27/JgnguGq8PPUYefF4faMZ8dm5qaBn3QSqVS/by5uTlaWloG9ev9/y86+F8DgGNXi3PBMFWp4TnKTzEAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACApLHWAxyuubk5Vq5cWf0cAOrNcDkXDqtAqFQq0dLSUusxAKBmhsu50FsMAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJAIBAEgEAgCQCAQAIBEIAEAiEACARCAAAIlAAAASgQAAJI21HqDWKn0Ho9R6CKhHbx448ufUvUrfwVqPQAiEGPPkf9d6BKh7rf/7P7UeAXgLbzEAAEldXkFobm6OlStX1noMqGullNi3b19ERDQ1NUWlUqnxRAxHzc3NtR6hbtVlIFQqlWhpaan1GFD3Ro0aVesRgKPwFgMAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkAgEACARCABAIhAAgEQgAACJQAAAEoEAACQCAQBIBAIAkDQe7wNLKRER0d3d/Y4NAwAMrkPn7UPn8aM57kDo6emJiIhJkyYd71MAADXS09MTY8eOPer9lTJQQhxFX19fbN++PVpbW6NSqRz3gPxbd3d3TJo0KV5++eVoa2ur9TjvSnY8+Ox48Nnx4Hs377iUEj09PdHR0RENDUf/ToPjvoLQ0NAQEydOPN6H8zba2tredX8hhxs7Hnx2PPjsePC9W3f8dlcODvFNigBAIhAAgEQgDCNNTU3xrW99K5qammo9yruWHQ8+Ox58djz47Pj/8E2KAMC7lysIAEAiEACARCAAAIlAAAASgTDI1q9fHwsWLIiOjo6oVCrxwAMPHPXYq666KiqVSnz/+9/vd/vu3bvjsssui7a2thg3blxceeWVsXfv3sEd/ARyLDveunVrfPrTn46xY8fG6NGjY+bMmbFt27bq/b29vdHV1RXvfe97Y8yYMfG5z30uXn311SF8FcPbQDveu3dvLFq0KCZOnBgtLS0xbdq0uOeee/odY8dv75ZbbomZM2dGa2trjB8/Pj772c/Gs88+2++YY9nhtm3bYv78+TFq1KgYP358LFmyJA4ePDiUL2XYGmjHu3fvjmuuuSbOOuusaGlpicmTJ8e1114br732Wr/nqZcdC4RB9vrrr8e5554bS5cufdvjli9fHps2bYqOjo5032WXXRbPPPNMrF69Oh566KFYv359fPnLXx6skU84A+34z3/+c3z84x+PqVOnxsMPPxxPPfVUfOMb34jm5ubqMddff308+OCDsWzZsli3bl1s3749Lr744qF6CcPeQDu+4YYbYtWqVXH//ffH1q1b47rrrotFixbFihUrqsfY8dtbt25ddHV1xaZNm2L16tVx4MCBmD17drz++uvVYwba4Ztvvhnz58+P/fv3x4YNG+KnP/1p3HffffHNb36zFi9p2Blox9u3b4/t27fH7bffHlu2bIn77rsvVq1aFVdeeWX1Oepqx4UhExFl+fLl6fa//e1v5X3ve1/ZsmVLmTJlSvne975Xve+Pf/xjiYjy+9//vnrbypUrS6VSKa+88soQTH1iOdKOL7nkkvL5z3/+qI/Zs2dPGTFiRFm2bFn1tq1bt5aIKBs3bhysUU9YR9rx9OnTy80339zvtvPPP798/etfL6XY8fHYtWtXiYiybt26Usqx7fBXv/pVaWhoKDt37qwec/fdd5e2trayb9++oX0BJ4C37vhIfvazn5WRI0eWAwcOlFLqa8euINRYX19fXH755bFkyZKYPn16un/jxo0xbty4+MhHPlK97aKLLoqGhoZ47LHHhnLUE1JfX1/88pe/jA984AMxZ86cGD9+fMyaNavfJfLHH388Dhw4EBdddFH1tqlTp8bkyZNj48aNNZj6xHPBBRfEihUr4pVXXolSSqxduzaee+65mD17dkTY8fE4dFn75JNPjohj2+HGjRvjnHPOiQkTJlSPmTNnTnR3d8czzzwzhNOfGN6646Md09bWFo2N//rVRfW0Y4FQY7fddls0NjbGtddee8T7d+7cGePHj+93W2NjY5x88smxc+fOoRjxhLZr167Yu3dv3HrrrTF37tz4zW9+EwsXLoyLL7441q1bFxH/2vHIkSNj3Lhx/R47YcIEOz5Gd911V0ybNi0mTpwYI0eOjLlz58bSpUvjE5/4RETY8X+qr68vrrvuuvjYxz4WZ599dkQc2w537tzZ78R16P5D9/FvR9rxW/3973+Pb3/72/3e0q2nHR/3b3Pk/+7xxx+PH/zgB/HEE0/4ldmDpK+vLyIiPvOZz8T1118fERHnnXdebNiwIe6555648MILazneu8Zdd90VmzZtihUrVsSUKVNi/fr10dXVFR0dHf3+j5dj09XVFVu2bIlHH3201qO8aw204+7u7pg/f35MmzYtbrrppqEdbphwBaGGHnnkkdi1a1dMnjw5Ghsbo7GxMV566aVYvHhxnHbaaRER0d7eHrt27er3uIMHD8bu3bujvb29BlOfWE455ZRobGyMadOm9bv9gx/8YPWnGNrb22P//v2xZ8+efse8+uqrdnwM3njjjfja174Wd955ZyxYsCA+9KEPxaJFi+KSSy6J22+/PSLs+D+xaNGieOihh2Lt2rUxceLE6u3HssP29vb0Uw2H/mzP/3a0HR/S09MTc+fOjdbW1li+fHmMGDGiel897Vgg1NDll18eTz31VDz55JPVj46OjliyZEn8+te/joiIzs7O2LNnTzz++OPVx61Zsyb6+vpi1qxZtRr9hDFy5MiYOXNm+nGx5557LqZMmRIRETNmzIgRI0bEb3/72+r9zz77bGzbti06OzuHdN4T0YEDB+LAgQPR0ND/n5OTTjqpegXHjgdWSolFixbF8uXLY82aNfH+97+/3/3HssPOzs54+umn+/1PxerVq6OtrS1Fcj0aaMcR/7pyMHv27Bg5cmSsWLGi3087RdTZjmv8TZLvej09PWXz5s1l8+bNJSLKnXfeWTZv3lxeeumlIx7/1p9iKKWUuXPnlg9/+MPlscceK48++mg588wzy6WXXjoE058YBtrxL37xizJixIjy4x//uDz//PPlrrvuKieddFJ55JFHqs9x1VVXlcmTJ5c1a9aUP/zhD6Wzs7N0dnbW6iUNOwPt+MILLyzTp08va9euLX/5y1/KvffeW5qbm8uPfvSj6nPY8dv7yle+UsaOHVsefvjhsmPHjurHP//5z+oxA+3w4MGD5eyzzy6zZ88uTz75ZFm1alU59dRTy4033liLlzTsDLTj1157rcyaNaucc8455YUXXuh3zMGDB0sp9bVjgTDI1q5dWyIifXzhC1844vFHCoR//OMf5dJLLy1jxowpbW1t5Ytf/GLp6ekZ/OFPEMey45/85CfljDPOKM3NzeXcc88tDzzwQL/neOONN8rVV19d3vOe95RRo0aVhQsXlh07dgzxKxm+Btrxjh07yhVXXFE6OjpKc3NzOeuss8odd9xR+vr6qs9hx2/vSPuNiHLvvfdWjzmWHb744otl3rx5paWlpZxyyill8eLF1R/Rq3cD7fhof88jovz1r3+tPk+97NivewYAEt+DAAAkAgEASAQCAJAIBAAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgHq1M6dO+Oaa66J008/PZqammLSpEmxYMGC6i8DOu2006JSqUSlUonRo0fH+eefH8uWLas+/qabborzzjuvRtMDg00gQB168cUXY8aMGbFmzZr47ne/G08//XSsWrUqPvnJT0ZXV1f1uJtvvjl27NgRmzdvjpkzZ8Yll1wSGzZsqOHkwFBprPUAwNC7+uqro1KpxO9+97sYPXp09fbp06fHl770peqfW1tbo729Pdrb22Pp0qVx//33x4MPPhgXXHBBLcYGhpArCFBndu/eHatWrYqurq5+cXDIuHHjjvi4xsbGGDFiROzfv3+QJwSGA1cQoM688MILUUqJqVOnHvNj9u/fH3fccUe89tpr8alPfWoQpwOGC1cQoM78J7/h/atf/WqMGTMmRo0aFbfddlvceuutMX/+/EGcDhguXEGAOnPmmWdGpVKJP/3pTwMeu2TJkrjiiitizJgxMWHChKhUKkMwITAcuIIAdebkk0+OOXPmxNKlS+P1119P9+/Zs6f6+SmnnBJnnHFGtLe3iwOoMwIB6tDSpUvjzTffjI9+9KPx85//PJ5//vnYunVr/PCHP4zOzs5ajwcMA95igDp0+umnxxNPPBHf+c53YvHixbFjx4449dRTY8aMGXH33XfXejxgGKiU/+Q7lgCAuuAtBgAgEQgAQCIQAIBEIAAAiUAAABKBAAAkAgEASAQCAJAIBAAgEQgAQCIQAIDk/wF2odeJRdP4tAAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=data,x=data.CPI)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Unemployment'>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=data,x=data.Unemployment)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Nombre d'observations considérées comme des outliers à plus de 75% non-contigus :  156 \n",
      "\n",
      "Nombre d'observations considérées comme des outliers à moins 25% non-contigus :  4\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Unemployment'>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Identifier les outliers avec la méthode IQR\n",
    "Q1 = data['Unemployment'].quantile(0.25)\n",
    "Q3 = data['Unemployment'].quantile(0.75)\n",
    "IQR = Q3 - Q1\n",
    "\n",
    "k = 1.5  # Facteur de seuil pour définir les outliers\n",
    "lower_limit = Q1 - k * IQR\n",
    "upper_limit = Q3 + k * IQR\n",
    "\n",
    "outliers = data[(data['Unemployment'] < lower_limit) | (data['Unemployment'] > upper_limit)]\n",
    "\n",
    "# Diviser les outliers en deux catégories\n",
    "upper_limit2 = 14\n",
    "lower_limit2 = 4\n",
    "\n",
    "outliers_contigus = data[(data['Unemployment'] > upper_limit) & (data['Unemployment'] <= upper_limit2)]\n",
    "outliers_non_contigus = data[data['Unemployment'] > upper_limit2]\n",
    "outliers_below_Q1 = data[data['Unemployment'] < lower_limit2]\n",
    "print(\"Nombre d'observations considérées comme des outliers à plus de 75% non-contigus : \", len(outliers_non_contigus), \"\\n\")\n",
    "print(\"Nombre d'observations considérées comme des outliers à moins 25% non-contigus : \", len(outliers_below_Q1))\n",
    "\n",
    "data.loc[data['Unemployment'] > upper_limit, 'Unemployment'] = upper_limit\n",
    "data.loc[data['Unemployment'] < lower_limit, 'Unemployment'] = lower_limit\n",
    "\n",
    "sns.boxplot(data=data,x=data.Unemployment)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>Store</th>\n",
       "      <th>Date</th>\n",
       "      <th>Daily_Sales</th>\n",
       "      <th>Holiday_Flag</th>\n",
       "      <th>Temperature</th>\n",
       "      <th>Fuel_Price</th>\n",
       "      <th>CPI</th>\n",
       "      <th>Unemployment</th>\n",
       "      <th>Year</th>\n",
       "      <th>Month</th>\n",
       "      <th>Day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-05-02</td>\n",
       "      <td>1643690.90</td>\n",
       "      <td>0</td>\n",
       "      <td>42.31</td>\n",
       "      <td>2.572</td>\n",
       "      <td>211.096358</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-12-02</td>\n",
       "      <td>1641957.44</td>\n",
       "      <td>1</td>\n",
       "      <td>38.51</td>\n",
       "      <td>2.548</td>\n",
       "      <td>211.242170</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>12</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-02-19</td>\n",
       "      <td>1611968.17</td>\n",
       "      <td>0</td>\n",
       "      <td>39.93</td>\n",
       "      <td>2.514</td>\n",
       "      <td>211.289143</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>2</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-02-26</td>\n",
       "      <td>1409727.59</td>\n",
       "      <td>0</td>\n",
       "      <td>46.63</td>\n",
       "      <td>2.561</td>\n",
       "      <td>211.319643</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>2</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2010-05-03</td>\n",
       "      <td>1554806.68</td>\n",
       "      <td>0</td>\n",
       "      <td>46.50</td>\n",
       "      <td>2.625</td>\n",
       "      <td>211.350143</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6430</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-09-28</td>\n",
       "      <td>713173.95</td>\n",
       "      <td>0</td>\n",
       "      <td>64.88</td>\n",
       "      <td>3.997</td>\n",
       "      <td>192.013558</td>\n",
       "      <td>8.684</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6431</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-05-10</td>\n",
       "      <td>733455.07</td>\n",
       "      <td>0</td>\n",
       "      <td>64.89</td>\n",
       "      <td>3.985</td>\n",
       "      <td>192.170412</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6432</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-12-10</td>\n",
       "      <td>734464.36</td>\n",
       "      <td>0</td>\n",
       "      <td>54.47</td>\n",
       "      <td>4.000</td>\n",
       "      <td>192.327265</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>12</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6433</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-10-19</td>\n",
       "      <td>718125.53</td>\n",
       "      <td>0</td>\n",
       "      <td>56.47</td>\n",
       "      <td>3.969</td>\n",
       "      <td>192.330854</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>10</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6434</th>\n",
       "      <td>45</td>\n",
       "      <td>2012-10-26</td>\n",
       "      <td>760281.43</td>\n",
       "      <td>0</td>\n",
       "      <td>58.85</td>\n",
       "      <td>3.882</td>\n",
       "      <td>192.308899</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>10</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6435 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Store        Date  Daily_Sales  Holiday_Flag  Temperature  Fuel_Price  \\\n",
       "0         1  2010-05-02   1643690.90             0        42.31       2.572   \n",
       "1         1  2010-12-02   1641957.44             1        38.51       2.548   \n",
       "2         1  2010-02-19   1611968.17             0        39.93       2.514   \n",
       "3         1  2010-02-26   1409727.59             0        46.63       2.561   \n",
       "4         1  2010-05-03   1554806.68             0        46.50       2.625   \n",
       "...     ...         ...          ...           ...          ...         ...   \n",
       "6430     45  2012-09-28    713173.95             0        64.88       3.997   \n",
       "6431     45  2012-05-10    733455.07             0        64.89       3.985   \n",
       "6432     45  2012-12-10    734464.36             0        54.47       4.000   \n",
       "6433     45  2012-10-19    718125.53             0        56.47       3.969   \n",
       "6434     45  2012-10-26    760281.43             0        58.85       3.882   \n",
       "\n",
       "             CPI  Unemployment  Year  Month  Day  \n",
       "0     211.096358         8.106  2010      5    2  \n",
       "1     211.242170         8.106  2010     12    2  \n",
       "2     211.289143         8.106  2010      2   19  \n",
       "3     211.319643         8.106  2010      2   26  \n",
       "4     211.350143         8.106  2010      5    3  \n",
       "...          ...           ...   ...    ...  ...  \n",
       "6430  192.013558         8.684  2012      9   28  \n",
       "6431  192.170412         8.667  2012      5   10  \n",
       "6432  192.327265         8.667  2012     12   10  \n",
       "6433  192.330854         8.667  2012     10   19  \n",
       "6434  192.308899         8.667  2012     10   26  \n",
       "\n",
       "[6435 rows x 11 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Extract relevant features from the 'Date' column\n",
    "data['Year'] = pd.to_datetime(data['Date']).dt.year\n",
    "data['Month'] = pd.to_datetime(data['Date']).dt.month\n",
    "data['Day'] = pd.to_datetime(data['Date']).dt.day\n",
    "\n",
    "#data.drop('Date', axis=1, inplace=True)\n",
    "#encoded_data = pd.DataFrame([data['Year'],data['Month'], data['DayOfWeek']], columns=(['Year', 'Month', 'DayOfWeek']))\n",
    "\n",
    "# Concatenate the encoded features with the original DataFrame\n",
    "#data_encoded = pd.concat([data.drop(['Year', 'Month', 'DayOfWeek'], axis=1), encoded_data], axis=1)\n",
    "#data_encoded\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = data.drop(['Date'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>Store</th>\n",
       "      <th>Daily_Sales</th>\n",
       "      <th>Holiday_Flag</th>\n",
       "      <th>Temperature</th>\n",
       "      <th>Fuel_Price</th>\n",
       "      <th>CPI</th>\n",
       "      <th>Unemployment</th>\n",
       "      <th>Year</th>\n",
       "      <th>Month</th>\n",
       "      <th>Day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1643690.90</td>\n",
       "      <td>0</td>\n",
       "      <td>42.31</td>\n",
       "      <td>2.572</td>\n",
       "      <td>211.096358</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1641957.44</td>\n",
       "      <td>1</td>\n",
       "      <td>38.51</td>\n",
       "      <td>2.548</td>\n",
       "      <td>211.242170</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>12</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1611968.17</td>\n",
       "      <td>0</td>\n",
       "      <td>39.93</td>\n",
       "      <td>2.514</td>\n",
       "      <td>211.289143</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>2</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1409727.59</td>\n",
       "      <td>0</td>\n",
       "      <td>46.63</td>\n",
       "      <td>2.561</td>\n",
       "      <td>211.319643</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>2</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1554806.68</td>\n",
       "      <td>0</td>\n",
       "      <td>46.50</td>\n",
       "      <td>2.625</td>\n",
       "      <td>211.350143</td>\n",
       "      <td>8.106</td>\n",
       "      <td>2010</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6430</th>\n",
       "      <td>45</td>\n",
       "      <td>713173.95</td>\n",
       "      <td>0</td>\n",
       "      <td>64.88</td>\n",
       "      <td>3.997</td>\n",
       "      <td>192.013558</td>\n",
       "      <td>8.684</td>\n",
       "      <td>2012</td>\n",
       "      <td>9</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6431</th>\n",
       "      <td>45</td>\n",
       "      <td>733455.07</td>\n",
       "      <td>0</td>\n",
       "      <td>64.89</td>\n",
       "      <td>3.985</td>\n",
       "      <td>192.170412</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6432</th>\n",
       "      <td>45</td>\n",
       "      <td>734464.36</td>\n",
       "      <td>0</td>\n",
       "      <td>54.47</td>\n",
       "      <td>4.000</td>\n",
       "      <td>192.327265</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>12</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6433</th>\n",
       "      <td>45</td>\n",
       "      <td>718125.53</td>\n",
       "      <td>0</td>\n",
       "      <td>56.47</td>\n",
       "      <td>3.969</td>\n",
       "      <td>192.330854</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>10</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6434</th>\n",
       "      <td>45</td>\n",
       "      <td>760281.43</td>\n",
       "      <td>0</td>\n",
       "      <td>58.85</td>\n",
       "      <td>3.882</td>\n",
       "      <td>192.308899</td>\n",
       "      <td>8.667</td>\n",
       "      <td>2012</td>\n",
       "      <td>10</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6435 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Store  Daily_Sales  Holiday_Flag  Temperature  Fuel_Price         CPI  \\\n",
       "0         1   1643690.90             0        42.31       2.572  211.096358   \n",
       "1         1   1641957.44             1        38.51       2.548  211.242170   \n",
       "2         1   1611968.17             0        39.93       2.514  211.289143   \n",
       "3         1   1409727.59             0        46.63       2.561  211.319643   \n",
       "4         1   1554806.68             0        46.50       2.625  211.350143   \n",
       "...     ...          ...           ...          ...         ...         ...   \n",
       "6430     45    713173.95             0        64.88       3.997  192.013558   \n",
       "6431     45    733455.07             0        64.89       3.985  192.170412   \n",
       "6432     45    734464.36             0        54.47       4.000  192.327265   \n",
       "6433     45    718125.53             0        56.47       3.969  192.330854   \n",
       "6434     45    760281.43             0        58.85       3.882  192.308899   \n",
       "\n",
       "      Unemployment  Year  Month  Day  \n",
       "0            8.106  2010      5    2  \n",
       "1            8.106  2010     12    2  \n",
       "2            8.106  2010      2   19  \n",
       "3            8.106  2010      2   26  \n",
       "4            8.106  2010      5    3  \n",
       "...            ...   ...    ...  ...  \n",
       "6430         8.684  2012      9   28  \n",
       "6431         8.667  2012      5   10  \n",
       "6432         8.667  2012     12   10  \n",
       "6433         8.667  2012     10   19  \n",
       "6434         8.667  2012     10   26  \n",
       "\n",
       "[6435 rows x 10 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store             int64\n",
       "Daily_Sales     float64\n",
       "Holiday_Flag      int64\n",
       "Temperature     float64\n",
       "Fuel_Price      float64\n",
       "CPI             float64\n",
       "Unemployment    float64\n",
       "Year              int64\n",
       "Month             int64\n",
       "Day               int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pycaret Linear Regression Model Elaboration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pycaret.regression import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_c2db2_row8_col1, #T_c2db2_row12_col1 {\n",
       "  background-color: lightgreen;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_c2db2\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_c2db2_level0_col0\" class=\"col_heading level0 col0\" >Description</th>\n",
       "      <th id=\"T_c2db2_level0_col1\" class=\"col_heading level0 col1\" >Value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "      <td id=\"T_c2db2_row0_col0\" class=\"data row0 col0\" >Session id</td>\n",
       "      <td id=\"T_c2db2_row0_col1\" class=\"data row0 col1\" >8701</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "      <td id=\"T_c2db2_row1_col0\" class=\"data row1 col0\" >Target</td>\n",
       "      <td id=\"T_c2db2_row1_col1\" class=\"data row1 col1\" >Daily_Sales</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
       "      <td id=\"T_c2db2_row2_col0\" class=\"data row2 col0\" >Target type</td>\n",
       "      <td id=\"T_c2db2_row2_col1\" class=\"data row2 col1\" >Regression</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
       "      <td id=\"T_c2db2_row3_col0\" class=\"data row3 col0\" >Original data shape</td>\n",
       "      <td id=\"T_c2db2_row3_col1\" class=\"data row3 col1\" >(6435, 10)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
       "      <td id=\"T_c2db2_row4_col0\" class=\"data row4 col0\" >Transformed data shape</td>\n",
       "      <td id=\"T_c2db2_row4_col1\" class=\"data row4 col1\" >(6435, 10)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
       "      <td id=\"T_c2db2_row5_col0\" class=\"data row5 col0\" >Transformed train set shape</td>\n",
       "      <td id=\"T_c2db2_row5_col1\" class=\"data row5 col1\" >(4504, 10)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
       "      <td id=\"T_c2db2_row6_col0\" class=\"data row6 col0\" >Transformed test set shape</td>\n",
       "      <td id=\"T_c2db2_row6_col1\" class=\"data row6 col1\" >(1931, 10)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
       "      <td id=\"T_c2db2_row7_col0\" class=\"data row7 col0\" >Numeric features</td>\n",
       "      <td id=\"T_c2db2_row7_col1\" class=\"data row7 col1\" >9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
       "      <td id=\"T_c2db2_row8_col0\" class=\"data row8 col0\" >Preprocess</td>\n",
       "      <td id=\"T_c2db2_row8_col1\" class=\"data row8 col1\" >True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
       "      <td id=\"T_c2db2_row9_col0\" class=\"data row9 col0\" >Imputation type</td>\n",
       "      <td id=\"T_c2db2_row9_col1\" class=\"data row9 col1\" >simple</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row10\" class=\"row_heading level0 row10\" >10</th>\n",
       "      <td id=\"T_c2db2_row10_col0\" class=\"data row10 col0\" >Numeric imputation</td>\n",
       "      <td id=\"T_c2db2_row10_col1\" class=\"data row10 col1\" >mean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row11\" class=\"row_heading level0 row11\" >11</th>\n",
       "      <td id=\"T_c2db2_row11_col0\" class=\"data row11 col0\" >Categorical imputation</td>\n",
       "      <td id=\"T_c2db2_row11_col1\" class=\"data row11 col1\" >mode</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row12\" class=\"row_heading level0 row12\" >12</th>\n",
       "      <td id=\"T_c2db2_row12_col0\" class=\"data row12 col0\" >Normalize</td>\n",
       "      <td id=\"T_c2db2_row12_col1\" class=\"data row12 col1\" >True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
       "      <td id=\"T_c2db2_row13_col0\" class=\"data row13 col0\" >Normalize method</td>\n",
       "      <td id=\"T_c2db2_row13_col1\" class=\"data row13 col1\" >minmax</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row14\" class=\"row_heading level0 row14\" >14</th>\n",
       "      <td id=\"T_c2db2_row14_col0\" class=\"data row14 col0\" >Fold Generator</td>\n",
       "      <td id=\"T_c2db2_row14_col1\" class=\"data row14 col1\" >KFold</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row15\" class=\"row_heading level0 row15\" >15</th>\n",
       "      <td id=\"T_c2db2_row15_col0\" class=\"data row15 col0\" >Fold Number</td>\n",
       "      <td id=\"T_c2db2_row15_col1\" class=\"data row15 col1\" >10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row16\" class=\"row_heading level0 row16\" >16</th>\n",
       "      <td id=\"T_c2db2_row16_col0\" class=\"data row16 col0\" >CPU Jobs</td>\n",
       "      <td id=\"T_c2db2_row16_col1\" class=\"data row16 col1\" >-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row17\" class=\"row_heading level0 row17\" >17</th>\n",
       "      <td id=\"T_c2db2_row17_col0\" class=\"data row17 col0\" >Use GPU</td>\n",
       "      <td id=\"T_c2db2_row17_col1\" class=\"data row17 col1\" >False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row18\" class=\"row_heading level0 row18\" >18</th>\n",
       "      <td id=\"T_c2db2_row18_col0\" class=\"data row18 col0\" >Log Experiment</td>\n",
       "      <td id=\"T_c2db2_row18_col1\" class=\"data row18 col1\" >False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row19\" class=\"row_heading level0 row19\" >19</th>\n",
       "      <td id=\"T_c2db2_row19_col0\" class=\"data row19 col0\" >Experiment Name</td>\n",
       "      <td id=\"T_c2db2_row19_col1\" class=\"data row19 col1\" >reg-default-name</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_c2db2_level0_row20\" class=\"row_heading level0 row20\" >20</th>\n",
       "      <td id=\"T_c2db2_row20_col0\" class=\"data row20 col0\" >USI</td>\n",
       "      <td id=\"T_c2db2_row20_col1\" class=\"data row20 col1\" >b442</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x25f20590550>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "reg = setup(data, target='Daily_Sales', normalize=True, normalize_method='minmax')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=0.5, booster=&#x27;gbtree&#x27;, callbacks=None,\n",
       "             colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,\n",
       "             early_stopping_rounds=None, enable_categorical=False,\n",
       "             eval_metric=None, gamma=0, gpu_id=-1, grow_policy=&#x27;depthwise&#x27;,\n",
       "             importance_type=None, interaction_constraints=&#x27;&#x27;,\n",
       "             learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,\n",
       "             max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,\n",
       "             missing=nan, monotone_constraints=&#x27;()&#x27;, n_estimators=100,\n",
       "             n_jobs=-1, num_parallel_tree=1, predictor=&#x27;auto&#x27;,\n",
       "             random_state=8701, reg_alpha=0, reg_lambda=1, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBRegressor<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=0.5, booster=&#x27;gbtree&#x27;, callbacks=None,\n",
       "             colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,\n",
       "             early_stopping_rounds=None, enable_categorical=False,\n",
       "             eval_metric=None, gamma=0, gpu_id=-1, grow_policy=&#x27;depthwise&#x27;,\n",
       "             importance_type=None, interaction_constraints=&#x27;&#x27;,\n",
       "             learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,\n",
       "             max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,\n",
       "             missing=nan, monotone_constraints=&#x27;()&#x27;, n_estimators=100,\n",
       "             n_jobs=-1, num_parallel_tree=1, predictor=&#x27;auto&#x27;,\n",
       "             random_state=8701, reg_alpha=0, reg_lambda=1, ...)</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "XGBRegressor(base_score=0.5, booster='gbtree', callbacks=None,\n",
       "             colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,\n",
       "             early_stopping_rounds=None, enable_categorical=False,\n",
       "             eval_metric=None, gamma=0, gpu_id=-1, grow_policy='depthwise',\n",
       "             importance_type=None, interaction_constraints='',\n",
       "             learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,\n",
       "             max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,\n",
       "             missing=nan, monotone_constraints='()', n_estimators=100,\n",
       "             n_jobs=-1, num_parallel_tree=1, predictor='auto',\n",
       "             random_state=8701, reg_alpha=0, reg_lambda=1, ...)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_models()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Initiated</th>\n",
       "      <td>. . . . . . . . . . . . . . . . . .</td>\n",
       "      <td>18:08:49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Status</th>\n",
       "      <td>. . . . . . . . . . . . . . . . . .</td>\n",
       "      <td>Selecting Estimator</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Estimator</th>\n",
       "      <td>. . . . . . . . . . . . . . . . . .</td>\n",
       "      <td>Compiling Library</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                   \n",
       "                                                                   \n",
       "Initiated  . . . . . . . . . . . . . . . . . .             18:08:49\n",
       "Status     . . . . . . . . . . . . . . . . . .  Selecting Estimator\n",
       "Estimator  . . . . . . . . . . . . . . . . . .    Compiling Library"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_0cec6_row10_col0, #T_0cec6_row10_col1, #T_0cec6_row10_col2, #T_0cec6_row10_col3, #T_0cec6_row10_col4, #T_0cec6_row10_col5 {\n",
       "  background: yellow;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_0cec6\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_0cec6_level0_col0\" class=\"col_heading level0 col0\" >MAE</th>\n",
       "      <th id=\"T_0cec6_level0_col1\" class=\"col_heading level0 col1\" >MSE</th>\n",
       "      <th id=\"T_0cec6_level0_col2\" class=\"col_heading level0 col2\" >RMSE</th>\n",
       "      <th id=\"T_0cec6_level0_col3\" class=\"col_heading level0 col3\" >R2</th>\n",
       "      <th id=\"T_0cec6_level0_col4\" class=\"col_heading level0 col4\" >RMSLE</th>\n",
       "      <th id=\"T_0cec6_level0_col5\" class=\"col_heading level0 col5\" >MAPE</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th class=\"index_name level0\" >Fold</th>\n",
       "      <th class=\"blank col0\" >&nbsp;</th>\n",
       "      <th class=\"blank col1\" >&nbsp;</th>\n",
       "      <th class=\"blank col2\" >&nbsp;</th>\n",
       "      <th class=\"blank col3\" >&nbsp;</th>\n",
       "      <th class=\"blank col4\" >&nbsp;</th>\n",
       "      <th class=\"blank col5\" >&nbsp;</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "      <td id=\"T_0cec6_row0_col0\" class=\"data row0 col0\" >52721.7383</td>\n",
       "      <td id=\"T_0cec6_row0_col1\" class=\"data row0 col1\" >7094510592.0000</td>\n",
       "      <td id=\"T_0cec6_row0_col2\" class=\"data row0 col2\" >84228.9141</td>\n",
       "      <td id=\"T_0cec6_row0_col3\" class=\"data row0 col3\" >0.9757</td>\n",
       "      <td id=\"T_0cec6_row0_col4\" class=\"data row0 col4\" >0.1059</td>\n",
       "      <td id=\"T_0cec6_row0_col5\" class=\"data row0 col5\" >0.0613</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "      <td id=\"T_0cec6_row1_col0\" class=\"data row1 col0\" >50161.0195</td>\n",
       "      <td id=\"T_0cec6_row1_col1\" class=\"data row1 col1\" >7583405056.0000</td>\n",
       "      <td id=\"T_0cec6_row1_col2\" class=\"data row1 col2\" >87082.7500</td>\n",
       "      <td id=\"T_0cec6_row1_col3\" class=\"data row1 col3\" >0.9753</td>\n",
       "      <td id=\"T_0cec6_row1_col4\" class=\"data row1 col4\" >0.0860</td>\n",
       "      <td id=\"T_0cec6_row1_col5\" class=\"data row1 col5\" >0.0557</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
       "      <td id=\"T_0cec6_row2_col0\" class=\"data row2 col0\" >62588.3398</td>\n",
       "      <td id=\"T_0cec6_row2_col1\" class=\"data row2 col1\" >11270412288.0000</td>\n",
       "      <td id=\"T_0cec6_row2_col2\" class=\"data row2 col2\" >106162.1953</td>\n",
       "      <td id=\"T_0cec6_row2_col3\" class=\"data row2 col3\" >0.9644</td>\n",
       "      <td id=\"T_0cec6_row2_col4\" class=\"data row2 col4\" >0.0956</td>\n",
       "      <td id=\"T_0cec6_row2_col5\" class=\"data row2 col5\" >0.0628</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
       "      <td id=\"T_0cec6_row3_col0\" class=\"data row3 col0\" >54049.5859</td>\n",
       "      <td id=\"T_0cec6_row3_col1\" class=\"data row3 col1\" >8522477568.0000</td>\n",
       "      <td id=\"T_0cec6_row3_col2\" class=\"data row3 col2\" >92317.2656</td>\n",
       "      <td id=\"T_0cec6_row3_col3\" class=\"data row3 col3\" >0.9736</td>\n",
       "      <td id=\"T_0cec6_row3_col4\" class=\"data row3 col4\" >0.0835</td>\n",
       "      <td id=\"T_0cec6_row3_col5\" class=\"data row3 col5\" >0.0559</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
       "      <td id=\"T_0cec6_row4_col0\" class=\"data row4 col0\" >50440.2930</td>\n",
       "      <td id=\"T_0cec6_row4_col1\" class=\"data row4 col1\" >6355119616.0000</td>\n",
       "      <td id=\"T_0cec6_row4_col2\" class=\"data row4 col2\" >79719.0078</td>\n",
       "      <td id=\"T_0cec6_row4_col3\" class=\"data row4 col3\" >0.9795</td>\n",
       "      <td id=\"T_0cec6_row4_col4\" class=\"data row4 col4\" >0.0985</td>\n",
       "      <td id=\"T_0cec6_row4_col5\" class=\"data row4 col5\" >0.0568</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
       "      <td id=\"T_0cec6_row5_col0\" class=\"data row5 col0\" >55670.2578</td>\n",
       "      <td id=\"T_0cec6_row5_col1\" class=\"data row5 col1\" >9608662016.0000</td>\n",
       "      <td id=\"T_0cec6_row5_col2\" class=\"data row5 col2\" >98023.7812</td>\n",
       "      <td id=\"T_0cec6_row5_col3\" class=\"data row5 col3\" >0.9691</td>\n",
       "      <td id=\"T_0cec6_row5_col4\" class=\"data row5 col4\" >0.1001</td>\n",
       "      <td id=\"T_0cec6_row5_col5\" class=\"data row5 col5\" >0.0625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
       "      <td id=\"T_0cec6_row6_col0\" class=\"data row6 col0\" >51194.2266</td>\n",
       "      <td id=\"T_0cec6_row6_col1\" class=\"data row6 col1\" >6248470016.0000</td>\n",
       "      <td id=\"T_0cec6_row6_col2\" class=\"data row6 col2\" >79047.2656</td>\n",
       "      <td id=\"T_0cec6_row6_col3\" class=\"data row6 col3\" >0.9809</td>\n",
       "      <td id=\"T_0cec6_row6_col4\" class=\"data row6 col4\" >0.0878</td>\n",
       "      <td id=\"T_0cec6_row6_col5\" class=\"data row6 col5\" >0.0569</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
       "      <td id=\"T_0cec6_row7_col0\" class=\"data row7 col0\" >52440.3828</td>\n",
       "      <td id=\"T_0cec6_row7_col1\" class=\"data row7 col1\" >6610165248.0000</td>\n",
       "      <td id=\"T_0cec6_row7_col2\" class=\"data row7 col2\" >81302.9219</td>\n",
       "      <td id=\"T_0cec6_row7_col3\" class=\"data row7 col3\" >0.9787</td>\n",
       "      <td id=\"T_0cec6_row7_col4\" class=\"data row7 col4\" >0.0849</td>\n",
       "      <td id=\"T_0cec6_row7_col5\" class=\"data row7 col5\" >0.0570</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
       "      <td id=\"T_0cec6_row8_col0\" class=\"data row8 col0\" >53432.1250</td>\n",
       "      <td id=\"T_0cec6_row8_col1\" class=\"data row8 col1\" >6348822016.0000</td>\n",
       "      <td id=\"T_0cec6_row8_col2\" class=\"data row8 col2\" >79679.4922</td>\n",
       "      <td id=\"T_0cec6_row8_col3\" class=\"data row8 col3\" >0.9779</td>\n",
       "      <td id=\"T_0cec6_row8_col4\" class=\"data row8 col4\" >0.1839</td>\n",
       "      <td id=\"T_0cec6_row8_col5\" class=\"data row8 col5\" >0.0577</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
       "      <td id=\"T_0cec6_row9_col0\" class=\"data row9 col0\" >47908.0195</td>\n",
       "      <td id=\"T_0cec6_row9_col1\" class=\"data row9 col1\" >5803044352.0000</td>\n",
       "      <td id=\"T_0cec6_row9_col2\" class=\"data row9 col2\" >76177.7188</td>\n",
       "      <td id=\"T_0cec6_row9_col3\" class=\"data row9 col3\" >0.9821</td>\n",
       "      <td id=\"T_0cec6_row9_col4\" class=\"data row9 col4\" >0.0788</td>\n",
       "      <td id=\"T_0cec6_row9_col5\" class=\"data row9 col5\" >0.0527</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row10\" class=\"row_heading level0 row10\" >Mean</th>\n",
       "      <td id=\"T_0cec6_row10_col0\" class=\"data row10 col0\" >53060.5988</td>\n",
       "      <td id=\"T_0cec6_row10_col1\" class=\"data row10 col1\" >7544508876.8000</td>\n",
       "      <td id=\"T_0cec6_row10_col2\" class=\"data row10 col2\" >86374.1312</td>\n",
       "      <td id=\"T_0cec6_row10_col3\" class=\"data row10 col3\" >0.9757</td>\n",
       "      <td id=\"T_0cec6_row10_col4\" class=\"data row10 col4\" >0.1005</td>\n",
       "      <td id=\"T_0cec6_row10_col5\" class=\"data row10 col5\" >0.0579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_0cec6_level0_row11\" class=\"row_heading level0 row11\" >Std</th>\n",
       "      <td id=\"T_0cec6_row11_col0\" class=\"data row11 col0\" >3801.4441</td>\n",
       "      <td id=\"T_0cec6_row11_col1\" class=\"data row11 col1\" >1665330173.2997</td>\n",
       "      <td id=\"T_0cec6_row11_col2\" class=\"data row11 col2\" >9166.1474</td>\n",
       "      <td id=\"T_0cec6_row11_col3\" class=\"data row11 col3\" >0.0052</td>\n",
       "      <td id=\"T_0cec6_row11_col4\" class=\"data row11 col4\" >0.0290</td>\n",
       "      <td id=\"T_0cec6_row11_col5\" class=\"data row11 col5\" >0.0031</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x25f1f228750>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model=create_model(\"xgboost\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "448436a0b16c4954a749d2fd6ab817eb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(ToggleButtons(description='Plot Type:', icons=('',), options=(('Pipeline Plot', 'pipelin…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "evaluate_model(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_fe706_row10_col0, #T_fe706_row10_col1, #T_fe706_row10_col2, #T_fe706_row10_col3, #T_fe706_row10_col4, #T_fe706_row10_col5 {\n",
       "  background: yellow;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_fe706\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_fe706_level0_col0\" class=\"col_heading level0 col0\" >MAE</th>\n",
       "      <th id=\"T_fe706_level0_col1\" class=\"col_heading level0 col1\" >MSE</th>\n",
       "      <th id=\"T_fe706_level0_col2\" class=\"col_heading level0 col2\" >RMSE</th>\n",
       "      <th id=\"T_fe706_level0_col3\" class=\"col_heading level0 col3\" >R2</th>\n",
       "      <th id=\"T_fe706_level0_col4\" class=\"col_heading level0 col4\" >RMSLE</th>\n",
       "      <th id=\"T_fe706_level0_col5\" class=\"col_heading level0 col5\" >MAPE</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th class=\"index_name level0\" >Fold</th>\n",
       "      <th class=\"blank col0\" >&nbsp;</th>\n",
       "      <th class=\"blank col1\" >&nbsp;</th>\n",
       "      <th class=\"blank col2\" >&nbsp;</th>\n",
       "      <th class=\"blank col3\" >&nbsp;</th>\n",
       "      <th class=\"blank col4\" >&nbsp;</th>\n",
       "      <th class=\"blank col5\" >&nbsp;</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "      <td id=\"T_fe706_row0_col0\" class=\"data row0 col0\" >72144.2344</td>\n",
       "      <td id=\"T_fe706_row0_col1\" class=\"data row0 col1\" >13923403776.0000</td>\n",
       "      <td id=\"T_fe706_row0_col2\" class=\"data row0 col2\" >117997.4766</td>\n",
       "      <td id=\"T_fe706_row0_col3\" class=\"data row0 col3\" >0.9524</td>\n",
       "      <td id=\"T_fe706_row0_col4\" class=\"data row0 col4\" >0.1232</td>\n",
       "      <td id=\"T_fe706_row0_col5\" class=\"data row0 col5\" >0.0855</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "      <td id=\"T_fe706_row1_col0\" class=\"data row1 col0\" >67364.0469</td>\n",
       "      <td id=\"T_fe706_row1_col1\" class=\"data row1 col1\" >13027191808.0000</td>\n",
       "      <td id=\"T_fe706_row1_col2\" class=\"data row1 col2\" >114136.7266</td>\n",
       "      <td id=\"T_fe706_row1_col3\" class=\"data row1 col3\" >0.9575</td>\n",
       "      <td id=\"T_fe706_row1_col4\" class=\"data row1 col4\" >0.1079</td>\n",
       "      <td id=\"T_fe706_row1_col5\" class=\"data row1 col5\" >0.0743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
       "      <td id=\"T_fe706_row2_col0\" class=\"data row2 col0\" >78961.5078</td>\n",
       "      <td id=\"T_fe706_row2_col1\" class=\"data row2 col1\" >16434673664.0000</td>\n",
       "      <td id=\"T_fe706_row2_col2\" class=\"data row2 col2\" >128197.7891</td>\n",
       "      <td id=\"T_fe706_row2_col3\" class=\"data row2 col3\" >0.9482</td>\n",
       "      <td id=\"T_fe706_row2_col4\" class=\"data row2 col4\" >0.1132</td>\n",
       "      <td id=\"T_fe706_row2_col5\" class=\"data row2 col5\" >0.0808</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
       "      <td id=\"T_fe706_row3_col0\" class=\"data row3 col0\" >72114.8594</td>\n",
       "      <td id=\"T_fe706_row3_col1\" class=\"data row3 col1\" >16118704128.0000</td>\n",
       "      <td id=\"T_fe706_row3_col2\" class=\"data row3 col2\" >126959.4609</td>\n",
       "      <td id=\"T_fe706_row3_col3\" class=\"data row3 col3\" >0.9501</td>\n",
       "      <td id=\"T_fe706_row3_col4\" class=\"data row3 col4\" >0.1129</td>\n",
       "      <td id=\"T_fe706_row3_col5\" class=\"data row3 col5\" >0.0774</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
       "      <td id=\"T_fe706_row4_col0\" class=\"data row4 col0\" >63425.8203</td>\n",
       "      <td id=\"T_fe706_row4_col1\" class=\"data row4 col1\" >9442840576.0000</td>\n",
       "      <td id=\"T_fe706_row4_col2\" class=\"data row4 col2\" >97174.2812</td>\n",
       "      <td id=\"T_fe706_row4_col3\" class=\"data row4 col3\" >0.9695</td>\n",
       "      <td id=\"T_fe706_row4_col4\" class=\"data row4 col4\" >0.0970</td>\n",
       "      <td id=\"T_fe706_row4_col5\" class=\"data row4 col5\" >0.0695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
       "      <td id=\"T_fe706_row5_col0\" class=\"data row5 col0\" >66351.4609</td>\n",
       "      <td id=\"T_fe706_row5_col1\" class=\"data row5 col1\" >13681622016.0000</td>\n",
       "      <td id=\"T_fe706_row5_col2\" class=\"data row5 col2\" >116968.4688</td>\n",
       "      <td id=\"T_fe706_row5_col3\" class=\"data row5 col3\" >0.9560</td>\n",
       "      <td id=\"T_fe706_row5_col4\" class=\"data row5 col4\" >0.1107</td>\n",
       "      <td id=\"T_fe706_row5_col5\" class=\"data row5 col5\" >0.0740</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
       "      <td id=\"T_fe706_row6_col0\" class=\"data row6 col0\" >58300.6836</td>\n",
       "      <td id=\"T_fe706_row6_col1\" class=\"data row6 col1\" >8188753920.0000</td>\n",
       "      <td id=\"T_fe706_row6_col2\" class=\"data row6 col2\" >90491.7344</td>\n",
       "      <td id=\"T_fe706_row6_col3\" class=\"data row6 col3\" >0.9750</td>\n",
       "      <td id=\"T_fe706_row6_col4\" class=\"data row6 col4\" >0.0904</td>\n",
       "      <td id=\"T_fe706_row6_col5\" class=\"data row6 col5\" >0.0624</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
       "      <td id=\"T_fe706_row7_col0\" class=\"data row7 col0\" >65851.5703</td>\n",
       "      <td id=\"T_fe706_row7_col1\" class=\"data row7 col1\" >10858310656.0000</td>\n",
       "      <td id=\"T_fe706_row7_col2\" class=\"data row7 col2\" >104203.2188</td>\n",
       "      <td id=\"T_fe706_row7_col3\" class=\"data row7 col3\" >0.9651</td>\n",
       "      <td id=\"T_fe706_row7_col4\" class=\"data row7 col4\" >0.1024</td>\n",
       "      <td id=\"T_fe706_row7_col5\" class=\"data row7 col5\" >0.0723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
       "      <td id=\"T_fe706_row8_col0\" class=\"data row8 col0\" >63356.6562</td>\n",
       "      <td id=\"T_fe706_row8_col1\" class=\"data row8 col1\" >10729723904.0000</td>\n",
       "      <td id=\"T_fe706_row8_col2\" class=\"data row8 col2\" >103584.3828</td>\n",
       "      <td id=\"T_fe706_row8_col3\" class=\"data row8 col3\" >0.9626</td>\n",
       "      <td id=\"T_fe706_row8_col4\" class=\"data row8 col4\" >0.0931</td>\n",
       "      <td id=\"T_fe706_row8_col5\" class=\"data row8 col5\" >0.0660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
       "      <td id=\"T_fe706_row9_col0\" class=\"data row9 col0\" >60723.4258</td>\n",
       "      <td id=\"T_fe706_row9_col1\" class=\"data row9 col1\" >10246772736.0000</td>\n",
       "      <td id=\"T_fe706_row9_col2\" class=\"data row9 col2\" >101226.3438</td>\n",
       "      <td id=\"T_fe706_row9_col3\" class=\"data row9 col3\" >0.9683</td>\n",
       "      <td id=\"T_fe706_row9_col4\" class=\"data row9 col4\" >0.0908</td>\n",
       "      <td id=\"T_fe706_row9_col5\" class=\"data row9 col5\" >0.0660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row10\" class=\"row_heading level0 row10\" >Mean</th>\n",
       "      <td id=\"T_fe706_row10_col0\" class=\"data row10 col0\" >66859.4266</td>\n",
       "      <td id=\"T_fe706_row10_col1\" class=\"data row10 col1\" >12265199718.4000</td>\n",
       "      <td id=\"T_fe706_row10_col2\" class=\"data row10 col2\" >110093.9883</td>\n",
       "      <td id=\"T_fe706_row10_col3\" class=\"data row10 col3\" >0.9605</td>\n",
       "      <td id=\"T_fe706_row10_col4\" class=\"data row10 col4\" >0.1042</td>\n",
       "      <td id=\"T_fe706_row10_col5\" class=\"data row10 col5\" >0.0728</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_fe706_level0_row11\" class=\"row_heading level0 row11\" >Std</th>\n",
       "      <td id=\"T_fe706_row11_col0\" class=\"data row11 col0\" >5818.0686</td>\n",
       "      <td id=\"T_fe706_row11_col1\" class=\"data row11 col1\" >2656402186.3040</td>\n",
       "      <td id=\"T_fe706_row11_col2\" class=\"data row11 col2\" >12021.3874</td>\n",
       "      <td id=\"T_fe706_row11_col3\" class=\"data row11 col3\" >0.0086</td>\n",
       "      <td id=\"T_fe706_row11_col4\" class=\"data row11 col4\" >0.0106</td>\n",
       "      <td id=\"T_fe706_row11_col5\" class=\"data row11 col5\" >0.0068</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x25f1eea81d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original model was better than the tuned model, hence it will be returned. NOTE: The display metrics are for the tuned model (not the original one).\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-2 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-2 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-2 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-2 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-2 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-2 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-2 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=0.5, booster=&#x27;gbtree&#x27;, callbacks=None,\n",
       "             colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,\n",
       "             early_stopping_rounds=None, enable_categorical=False,\n",
       "             eval_metric=None, gamma=0, gpu_id=-1, grow_policy=&#x27;depthwise&#x27;,\n",
       "             importance_type=None, interaction_constraints=&#x27;&#x27;,\n",
       "             learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,\n",
       "             max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,\n",
       "             missing=nan, monotone_constraints=&#x27;()&#x27;, n_estimators=100,\n",
       "             n_jobs=-1, num_parallel_tree=1, predictor=&#x27;auto&#x27;,\n",
       "             random_state=8701, reg_alpha=0, reg_lambda=1, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBRegressor<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=0.5, booster=&#x27;gbtree&#x27;, callbacks=None,\n",
       "             colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,\n",
       "             early_stopping_rounds=None, enable_categorical=False,\n",
       "             eval_metric=None, gamma=0, gpu_id=-1, grow_policy=&#x27;depthwise&#x27;,\n",
       "             importance_type=None, interaction_constraints=&#x27;&#x27;,\n",
       "             learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,\n",
       "             max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,\n",
       "             missing=nan, monotone_constraints=&#x27;()&#x27;, n_estimators=100,\n",
       "             n_jobs=-1, num_parallel_tree=1, predictor=&#x27;auto&#x27;,\n",
       "             random_state=8701, reg_alpha=0, reg_lambda=1, ...)</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "XGBRegressor(base_score=0.5, booster='gbtree', callbacks=None,\n",
       "             colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,\n",
       "             early_stopping_rounds=None, enable_categorical=False,\n",
       "             eval_metric=None, gamma=0, gpu_id=-1, grow_policy='depthwise',\n",
       "             importance_type=None, interaction_constraints='',\n",
       "             learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,\n",
       "             max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,\n",
       "             missing=nan, monotone_constraints='()', n_estimators=100,\n",
       "             n_jobs=-1, num_parallel_tree=1, predictor='auto',\n",
       "             random_state=8701, reg_alpha=0, reg_lambda=1, ...)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tune_model(model, search_library='optuna')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Daily Sales based on period between two dates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "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>Store</th>\n",
       "      <th>Daily_Sales</th>\n",
       "      <th>Holiday_Flag</th>\n",
       "      <th>Temperature</th>\n",
       "      <th>Fuel_Price</th>\n",
       "      <th>CPI</th>\n",
       "      <th>Unemployment</th>\n",
       "      <th>Year</th>\n",
       "      <th>Month</th>\n",
       "      <th>Day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>1</td>\n",
       "      <td>1453329.50</td>\n",
       "      <td>0</td>\n",
       "      <td>71.89</td>\n",
       "      <td>2.603</td>\n",
       "      <td>211.671989</td>\n",
       "      <td>7.8380</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>177</th>\n",
       "      <td>2</td>\n",
       "      <td>1827440.43</td>\n",
       "      <td>0</td>\n",
       "      <td>69.24</td>\n",
       "      <td>2.603</td>\n",
       "      <td>211.329874</td>\n",
       "      <td>8.1630</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>320</th>\n",
       "      <td>3</td>\n",
       "      <td>358784.10</td>\n",
       "      <td>0</td>\n",
       "      <td>73.60</td>\n",
       "      <td>2.603</td>\n",
       "      <td>214.984655</td>\n",
       "      <td>7.5640</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>463</th>\n",
       "      <td>4</td>\n",
       "      <td>1842821.02</td>\n",
       "      <td>0</td>\n",
       "      <td>63.96</td>\n",
       "      <td>2.619</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>7.1270</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>606</th>\n",
       "      <td>5</td>\n",
       "      <td>283178.12</td>\n",
       "      <td>0</td>\n",
       "      <td>71.10</td>\n",
       "      <td>2.603</td>\n",
       "      <td>212.226946</td>\n",
       "      <td>6.7680</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>749</th>\n",
       "      <td>6</td>\n",
       "      <td>1328468.89</td>\n",
       "      <td>0</td>\n",
       "      <td>70.69</td>\n",
       "      <td>2.603</td>\n",
       "      <td>213.190713</td>\n",
       "      <td>7.0070</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "      <td>7</td>\n",
       "      <td>448998.73</td>\n",
       "      <td>0</td>\n",
       "      <td>49.99</td>\n",
       "      <td>2.759</td>\n",
       "      <td>190.673824</td>\n",
       "      <td>9.1370</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1035</th>\n",
       "      <td>8</td>\n",
       "      <td>804105.49</td>\n",
       "      <td>0</td>\n",
       "      <td>68.70</td>\n",
       "      <td>2.603</td>\n",
       "      <td>215.031003</td>\n",
       "      <td>6.4330</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1178</th>\n",
       "      <td>9</td>\n",
       "      <td>495692.19</td>\n",
       "      <td>0</td>\n",
       "      <td>69.08</td>\n",
       "      <td>2.603</td>\n",
       "      <td>215.214134</td>\n",
       "      <td>6.5600</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1321</th>\n",
       "      <td>10</td>\n",
       "      <td>1645892.97</td>\n",
       "      <td>0</td>\n",
       "      <td>86.01</td>\n",
       "      <td>3.001</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>9.0030</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1464</th>\n",
       "      <td>11</td>\n",
       "      <td>1182490.46</td>\n",
       "      <td>0</td>\n",
       "      <td>75.11</td>\n",
       "      <td>2.603</td>\n",
       "      <td>214.984655</td>\n",
       "      <td>7.5640</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1607</th>\n",
       "      <td>12</td>\n",
       "      <td>850936.26</td>\n",
       "      <td>0</td>\n",
       "      <td>85.20</td>\n",
       "      <td>3.001</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>11.2185</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1750</th>\n",
       "      <td>13</td>\n",
       "      <td>1765584.48</td>\n",
       "      <td>0</td>\n",
       "      <td>68.74</td>\n",
       "      <td>2.853</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>7.7950</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1893</th>\n",
       "      <td>14</td>\n",
       "      <td>1855703.66</td>\n",
       "      <td>0</td>\n",
       "      <td>70.58</td>\n",
       "      <td>2.707</td>\n",
       "      <td>182.716838</td>\n",
       "      <td>8.7240</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2036</th>\n",
       "      <td>15</td>\n",
       "      <td>566945.95</td>\n",
       "      <td>0</td>\n",
       "      <td>59.69</td>\n",
       "      <td>2.840</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>8.0670</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2179</th>\n",
       "      <td>16</td>\n",
       "      <td>463977.54</td>\n",
       "      <td>0</td>\n",
       "      <td>59.39</td>\n",
       "      <td>2.759</td>\n",
       "      <td>190.673824</td>\n",
       "      <td>6.9860</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2322</th>\n",
       "      <td>17</td>\n",
       "      <td>829207.27</td>\n",
       "      <td>0</td>\n",
       "      <td>60.07</td>\n",
       "      <td>2.853</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>6.8850</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2465</th>\n",
       "      <td>18</td>\n",
       "      <td>948977.50</td>\n",
       "      <td>0</td>\n",
       "      <td>67.76</td>\n",
       "      <td>2.717</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>9.3310</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2608</th>\n",
       "      <td>19</td>\n",
       "      <td>1379456.30</td>\n",
       "      <td>0</td>\n",
       "      <td>59.91</td>\n",
       "      <td>2.840</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>8.0670</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2751</th>\n",
       "      <td>20</td>\n",
       "      <td>1933719.21</td>\n",
       "      <td>0</td>\n",
       "      <td>61.08</td>\n",
       "      <td>2.707</td>\n",
       "      <td>204.885097</td>\n",
       "      <td>7.4840</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2894</th>\n",
       "      <td>21</td>\n",
       "      <td>677158.39</td>\n",
       "      <td>0</td>\n",
       "      <td>70.28</td>\n",
       "      <td>2.603</td>\n",
       "      <td>211.329874</td>\n",
       "      <td>8.1630</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3037</th>\n",
       "      <td>22</td>\n",
       "      <td>905987.17</td>\n",
       "      <td>0</td>\n",
       "      <td>69.31</td>\n",
       "      <td>2.717</td>\n",
       "      <td>136.629757</td>\n",
       "      <td>8.5720</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3180</th>\n",
       "      <td>23</td>\n",
       "      <td>1129909.44</td>\n",
       "      <td>0</td>\n",
       "      <td>62.07</td>\n",
       "      <td>2.717</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>5.2870</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3323</th>\n",
       "      <td>24</td>\n",
       "      <td>1215273.20</td>\n",
       "      <td>0</td>\n",
       "      <td>66.88</td>\n",
       "      <td>2.840</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>8.2750</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3466</th>\n",
       "      <td>25</td>\n",
       "      <td>658640.14</td>\n",
       "      <td>0</td>\n",
       "      <td>57.56</td>\n",
       "      <td>2.707</td>\n",
       "      <td>204.885097</td>\n",
       "      <td>7.4840</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3609</th>\n",
       "      <td>26</td>\n",
       "      <td>923221.52</td>\n",
       "      <td>0</td>\n",
       "      <td>57.80</td>\n",
       "      <td>2.717</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>8.1490</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3752</th>\n",
       "      <td>27</td>\n",
       "      <td>1543532.83</td>\n",
       "      <td>0</td>\n",
       "      <td>70.19</td>\n",
       "      <td>2.840</td>\n",
       "      <td>136.629757</td>\n",
       "      <td>8.0210</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3895</th>\n",
       "      <td>28</td>\n",
       "      <td>1203080.41</td>\n",
       "      <td>0</td>\n",
       "      <td>85.20</td>\n",
       "      <td>3.001</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>11.2185</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4038</th>\n",
       "      <td>29</td>\n",
       "      <td>474698.01</td>\n",
       "      <td>0</td>\n",
       "      <td>69.31</td>\n",
       "      <td>2.717</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>10.5240</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4181</th>\n",
       "      <td>30</td>\n",
       "      <td>445475.30</td>\n",
       "      <td>0</td>\n",
       "      <td>70.28</td>\n",
       "      <td>2.603</td>\n",
       "      <td>211.329874</td>\n",
       "      <td>8.1630</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4324</th>\n",
       "      <td>31</td>\n",
       "      <td>1213981.64</td>\n",
       "      <td>0</td>\n",
       "      <td>70.28</td>\n",
       "      <td>2.603</td>\n",
       "      <td>211.329874</td>\n",
       "      <td>8.1630</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4467</th>\n",
       "      <td>32</td>\n",
       "      <td>1061089.56</td>\n",
       "      <td>0</td>\n",
       "      <td>66.14</td>\n",
       "      <td>2.759</td>\n",
       "      <td>190.673824</td>\n",
       "      <td>9.1370</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4610</th>\n",
       "      <td>33</td>\n",
       "      <td>224294.39</td>\n",
       "      <td>0</td>\n",
       "      <td>91.45</td>\n",
       "      <td>3.001</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>9.2650</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4753</th>\n",
       "      <td>34</td>\n",
       "      <td>865709.11</td>\n",
       "      <td>0</td>\n",
       "      <td>70.13</td>\n",
       "      <td>2.619</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>10.2100</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4896</th>\n",
       "      <td>35</td>\n",
       "      <td>771065.21</td>\n",
       "      <td>0</td>\n",
       "      <td>70.19</td>\n",
       "      <td>2.707</td>\n",
       "      <td>136.629757</td>\n",
       "      <td>8.7630</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5039</th>\n",
       "      <td>36</td>\n",
       "      <td>422169.47</td>\n",
       "      <td>0</td>\n",
       "      <td>74.66</td>\n",
       "      <td>2.567</td>\n",
       "      <td>210.440443</td>\n",
       "      <td>8.4760</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5182</th>\n",
       "      <td>37</td>\n",
       "      <td>529877.93</td>\n",
       "      <td>0</td>\n",
       "      <td>74.66</td>\n",
       "      <td>2.603</td>\n",
       "      <td>210.440443</td>\n",
       "      <td>8.4760</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5325</th>\n",
       "      <td>38</td>\n",
       "      <td>360256.58</td>\n",
       "      <td>0</td>\n",
       "      <td>85.20</td>\n",
       "      <td>3.001</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>11.2185</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5468</th>\n",
       "      <td>39</td>\n",
       "      <td>1219583.91</td>\n",
       "      <td>0</td>\n",
       "      <td>72.74</td>\n",
       "      <td>2.603</td>\n",
       "      <td>210.440443</td>\n",
       "      <td>8.4760</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5611</th>\n",
       "      <td>40</td>\n",
       "      <td>891152.33</td>\n",
       "      <td>0</td>\n",
       "      <td>62.01</td>\n",
       "      <td>2.717</td>\n",
       "      <td>132.756800</td>\n",
       "      <td>5.2870</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5754</th>\n",
       "      <td>41</td>\n",
       "      <td>1109216.35</td>\n",
       "      <td>0</td>\n",
       "      <td>62.67</td>\n",
       "      <td>2.759</td>\n",
       "      <td>190.673824</td>\n",
       "      <td>7.5080</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5897</th>\n",
       "      <td>42</td>\n",
       "      <td>481523.93</td>\n",
       "      <td>0</td>\n",
       "      <td>86.01</td>\n",
       "      <td>3.001</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>9.0030</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6040</th>\n",
       "      <td>43</td>\n",
       "      <td>657108.77</td>\n",
       "      <td>0</td>\n",
       "      <td>77.93</td>\n",
       "      <td>2.603</td>\n",
       "      <td>203.593429</td>\n",
       "      <td>10.2100</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6183</th>\n",
       "      <td>44</td>\n",
       "      <td>300152.45</td>\n",
       "      <td>0</td>\n",
       "      <td>68.74</td>\n",
       "      <td>2.853</td>\n",
       "      <td>126.234600</td>\n",
       "      <td>7.6100</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6326</th>\n",
       "      <td>45</td>\n",
       "      <td>690007.76</td>\n",
       "      <td>0</td>\n",
       "      <td>70.58</td>\n",
       "      <td>2.707</td>\n",
       "      <td>182.716838</td>\n",
       "      <td>8.7240</td>\n",
       "      <td>2010</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Store  Daily_Sales  Holiday_Flag  Temperature  Fuel_Price         CPI  \\\n",
       "34        1   1453329.50             0        71.89       2.603  211.671989   \n",
       "177       2   1827440.43             0        69.24       2.603  211.329874   \n",
       "320       3    358784.10             0        73.60       2.603  214.984655   \n",
       "463       4   1842821.02             0        63.96       2.619  126.234600   \n",
       "606       5    283178.12             0        71.10       2.603  212.226946   \n",
       "749       6   1328468.89             0        70.69       2.603  213.190713   \n",
       "892       7    448998.73             0        49.99       2.759  190.673824   \n",
       "1035      8    804105.49             0        68.70       2.603  215.031003   \n",
       "1178      9    495692.19             0        69.08       2.603  215.214134   \n",
       "1321     10   1645892.97             0        86.01       3.001  126.234600   \n",
       "1464     11   1182490.46             0        75.11       2.603  214.984655   \n",
       "1607     12    850936.26             0        85.20       3.001  126.234600   \n",
       "1750     13   1765584.48             0        68.74       2.853  126.234600   \n",
       "1893     14   1855703.66             0        70.58       2.707  182.716838   \n",
       "2036     15    566945.95             0        59.69       2.840  132.756800   \n",
       "2179     16    463977.54             0        59.39       2.759  190.673824   \n",
       "2322     17    829207.27             0        60.07       2.853  126.234600   \n",
       "2465     18    948977.50             0        67.76       2.717  132.756800   \n",
       "2608     19   1379456.30             0        59.91       2.840  132.756800   \n",
       "2751     20   1933719.21             0        61.08       2.707  204.885097   \n",
       "2894     21    677158.39             0        70.28       2.603  211.329874   \n",
       "3037     22    905987.17             0        69.31       2.717  136.629757   \n",
       "3180     23   1129909.44             0        62.07       2.717  132.756800   \n",
       "3323     24   1215273.20             0        66.88       2.840  132.756800   \n",
       "3466     25    658640.14             0        57.56       2.707  204.885097   \n",
       "3609     26    923221.52             0        57.80       2.717  132.756800   \n",
       "3752     27   1543532.83             0        70.19       2.840  136.629757   \n",
       "3895     28   1203080.41             0        85.20       3.001  126.234600   \n",
       "4038     29    474698.01             0        69.31       2.717  132.756800   \n",
       "4181     30    445475.30             0        70.28       2.603  211.329874   \n",
       "4324     31   1213981.64             0        70.28       2.603  211.329874   \n",
       "4467     32   1061089.56             0        66.14       2.759  190.673824   \n",
       "4610     33    224294.39             0        91.45       3.001  126.234600   \n",
       "4753     34    865709.11             0        70.13       2.619  126.234600   \n",
       "4896     35    771065.21             0        70.19       2.707  136.629757   \n",
       "5039     36    422169.47             0        74.66       2.567  210.440443   \n",
       "5182     37    529877.93             0        74.66       2.603  210.440443   \n",
       "5325     38    360256.58             0        85.20       3.001  126.234600   \n",
       "5468     39   1219583.91             0        72.74       2.603  210.440443   \n",
       "5611     40    891152.33             0        62.01       2.717  132.756800   \n",
       "5754     41   1109216.35             0        62.67       2.759  190.673824   \n",
       "5897     42    481523.93             0        86.01       3.001  126.234600   \n",
       "6040     43    657108.77             0        77.93       2.603  203.593429   \n",
       "6183     44    300152.45             0        68.74       2.853  126.234600   \n",
       "6326     45    690007.76             0        70.58       2.707  182.716838   \n",
       "\n",
       "      Unemployment  Year  Month  Day  \n",
       "34          7.8380  2010      1   10  \n",
       "177         8.1630  2010      1   10  \n",
       "320         7.5640  2010      1   10  \n",
       "463         7.1270  2010      1   10  \n",
       "606         6.7680  2010      1   10  \n",
       "749         7.0070  2010      1   10  \n",
       "892         9.1370  2010      1   10  \n",
       "1035        6.4330  2010      1   10  \n",
       "1178        6.5600  2010      1   10  \n",
       "1321        9.0030  2010      1   10  \n",
       "1464        7.5640  2010      1   10  \n",
       "1607       11.2185  2010      1   10  \n",
       "1750        7.7950  2010      1   10  \n",
       "1893        8.7240  2010      1   10  \n",
       "2036        8.0670  2010      1   10  \n",
       "2179        6.9860  2010      1   10  \n",
       "2322        6.8850  2010      1   10  \n",
       "2465        9.3310  2010      1   10  \n",
       "2608        8.0670  2010      1   10  \n",
       "2751        7.4840  2010      1   10  \n",
       "2894        8.1630  2010      1   10  \n",
       "3037        8.5720  2010      1   10  \n",
       "3180        5.2870  2010      1   10  \n",
       "3323        8.2750  2010      1   10  \n",
       "3466        7.4840  2010      1   10  \n",
       "3609        8.1490  2010      1   10  \n",
       "3752        8.0210  2010      1   10  \n",
       "3895       11.2185  2010      1   10  \n",
       "4038       10.5240  2010      1   10  \n",
       "4181        8.1630  2010      1   10  \n",
       "4324        8.1630  2010      1   10  \n",
       "4467        9.1370  2010      1   10  \n",
       "4610        9.2650  2010      1   10  \n",
       "4753       10.2100  2010      1   10  \n",
       "4896        8.7630  2010      1   10  \n",
       "5039        8.4760  2010      1   10  \n",
       "5182        8.4760  2010      1   10  \n",
       "5325       11.2185  2010      1   10  \n",
       "5468        8.4760  2010      1   10  \n",
       "5611        5.2870  2010      1   10  \n",
       "5754        7.5080  2010      1   10  \n",
       "5897        9.0030  2010      1   10  \n",
       "6040       10.2100  2010      1   10  \n",
       "6183        7.6100  2010      1   10  \n",
       "6326        8.7240  2010      1   10  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start_date = pd.to_datetime('2010-01-01')\n",
    "end_date = pd.to_datetime('2010-01-10')\n",
    "\n",
    "filtered_df = data[(data['Year'] >= start_date.year) & (data['Month'] >= start_date.month) & (data['Day'] >= start_date.day) &\n",
    "                   (data['Year'] <= end_date.year) & (data['Month'] <= end_date.month) & (data['Day'] <= end_date.day)]\n",
    "filtered_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let'us Try to predict Daily_Sales"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " The predicted Daily Sales are :$ 688340.0\n"
     ]
    }
   ],
   "source": [
    "#data['Date'] = pd.to_datetime(data['Date'])\n",
    "# Make predictions on new data\n",
    "new_data = pd.DataFrame([[45, 0, 70.58, 2.707, 182.716838, 8.724, 2010, 1, 10]],\n",
    "                        columns=['Store', 'Holiday_Flag', 'Temperature',\n",
    "                                 'Fuel_Price', 'CPI', 'Unemployment', 'Year', 'Month', 'Day'])\n",
    "new = [[45, 1, 29.67, 3.179, 182.571448, 8.724, 2010, 12, 31]]\n",
    "#prediction = model.predict(np.array(pd.DataFrame(new)))\n",
    "#print('Predicted number of sales: ', prediction)\n",
    "predictions = predict_model(model, data=new_data)\n",
    "\n",
    "# View the predicted values\n",
    "y_temp_predict = predictions['prediction_label'].values[0]\n",
    "print(f\" The predicted Daily Sales are :$ {np.round(y_temp_predict)}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Transformation Pipeline and Model Successfully Saved\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(Pipeline(memory=Memory(location=None),\n",
       "          steps=[('numerical_imputer',\n",
       "                  TransformerWrapper(include=['Store', 'Holiday_Flag',\n",
       "                                              'Temperature', 'Fuel_Price', 'CPI',\n",
       "                                              'Unemployment', 'Year', 'Month',\n",
       "                                              'Day'],\n",
       "                                     transformer=SimpleImputer())),\n",
       "                 ('categorical_imputer',\n",
       "                  TransformerWrapper(include=[],\n",
       "                                     transformer=SimpleImputer(strategy='most_frequent'))),\n",
       "                 ('normalize', TransformerWr...\n",
       "                               gamma=0, gpu_id=-1, grow_policy='depthwise',\n",
       "                               importance_type=None, interaction_constraints='',\n",
       "                               learning_rate=0.300000012, max_bin=256,\n",
       "                               max_cat_to_onehot=4, max_delta_step=0,\n",
       "                               max_depth=6, max_leaves=0, min_child_weight=1,\n",
       "                               missing=nan, monotone_constraints='()',\n",
       "                               n_estimators=100, n_jobs=-1, num_parallel_tree=1,\n",
       "                               predictor='auto', random_state=8701, reg_alpha=0,\n",
       "                               reg_lambda=1, ...))]),\n",
       " './models/Walmart.pkl')"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "save_model(model,\"./models/Walmart\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "pickle.dump(model, open('./models/walmart_model.pkl', 'wb'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Monsieur j'ai choisi d'utiliser sur streamlit le model sans dump ceci pour une bonne raison.Pour la prediction juste avant le save model nous avons comme daily sales: **$688340.0**. Sur Streamlit, nous avons **$688339.6** avec le model sans dump.Tandis qu'avec le model pickle dumpé on a **$620000.0** ce qui est trop éloigné de notre valeur réelle qui est: **$690007.76**."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2024 - All rights reserved - Bekombo Ntone Louis Jason Loic Walmart Daily_Sales Prediction Notebook"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}