prac_model.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "boolean-illustration",
   "metadata": {},
   "source": [
    "# Flight Ticket Price Prediction"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "expired-artist",
   "metadata": {},
   "source": [
    "### Importing the necessary libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "mechanical-design",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "second-packet",
   "metadata": {},
   "source": [
    "### Loading the train and test dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "reserved-patrick",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df=pd.read_csv('Data_Train.csv')\n",
    "test_df=pd.read_csv('Test_set.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "conservative-millennium",
   "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>Airline</th>\n",
       "      <th>Date_of_Journey</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>24/03/2019</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>01:10 22 Mar</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>non-stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>1/05/2019</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>13:15</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>9/06/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>04:25 10 Jun</td>\n",
       "      <td>19h</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>12/05/2019</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>23:30</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>01/03/2019</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>21:35</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline Date_of_Journey    Source Destination                  Route  \\\n",
       "0       IndiGo      24/03/2019  Banglore   New Delhi              BLR ? DEL   \n",
       "1    Air India       1/05/2019   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR   \n",
       "2  Jet Airways       9/06/2019     Delhi      Cochin  DEL ? LKO ? BOM ? COK   \n",
       "3       IndiGo      12/05/2019   Kolkata    Banglore        CCU ? NAG ? BLR   \n",
       "4       IndiGo      01/03/2019  Banglore   New Delhi        BLR ? NAG ? DEL   \n",
       "\n",
       "  Dep_Time  Arrival_Time Duration Total_Stops Additional_Info  Price  \n",
       "0    22:20  01:10 22 Mar   2h 50m    non-stop         No info   3897  \n",
       "1    05:50         13:15   7h 25m     2 stops         No info   7662  \n",
       "2    09:25  04:25 10 Jun      19h     2 stops         No info  13882  \n",
       "3    18:05         23:30   5h 25m      1 stop         No info   6218  \n",
       "4    16:50         21:35   4h 45m      1 stop         No info  13302  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "received-frontier",
   "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>Airline</th>\n",
       "      <th>Date_of_Journey</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>6/06/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? BOM ? COK</td>\n",
       "      <td>17:30</td>\n",
       "      <td>04:25 07 Jun</td>\n",
       "      <td>10h 55m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>12/05/2019</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? MAA ? BLR</td>\n",
       "      <td>06:20</td>\n",
       "      <td>10:20</td>\n",
       "      <td>4h</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>21/05/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? BOM ? COK</td>\n",
       "      <td>19:15</td>\n",
       "      <td>19:00 22 May</td>\n",
       "      <td>23h 45m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>In-flight meal not included</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Multiple carriers</td>\n",
       "      <td>21/05/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? BOM ? COK</td>\n",
       "      <td>08:00</td>\n",
       "      <td>21:00</td>\n",
       "      <td>13h</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Air Asia</td>\n",
       "      <td>24/06/2019</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>23:55</td>\n",
       "      <td>02:45 25 Jun</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>non-stop</td>\n",
       "      <td>No info</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Airline Date_of_Journey    Source Destination            Route  \\\n",
       "0        Jet Airways       6/06/2019     Delhi      Cochin  DEL ? BOM ? COK   \n",
       "1             IndiGo      12/05/2019   Kolkata    Banglore  CCU ? MAA ? BLR   \n",
       "2        Jet Airways      21/05/2019     Delhi      Cochin  DEL ? BOM ? COK   \n",
       "3  Multiple carriers      21/05/2019     Delhi      Cochin  DEL ? BOM ? COK   \n",
       "4           Air Asia      24/06/2019  Banglore       Delhi        BLR ? DEL   \n",
       "\n",
       "  Dep_Time  Arrival_Time Duration Total_Stops              Additional_Info  \n",
       "0    17:30  04:25 07 Jun  10h 55m      1 stop                      No info  \n",
       "1    06:20         10:20       4h      1 stop                      No info  \n",
       "2    19:15  19:00 22 May  23h 45m      1 stop  In-flight meal not included  \n",
       "3    08:00         21:00      13h      1 stop                      No info  \n",
       "4    23:55  02:45 25 Jun   2h 50m    non-stop                      No info  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "intellectual-silicon",
   "metadata": {},
   "source": [
    "### Appending the train and test dataset(since its a hackathon competition)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "shared-specification",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df=train_df.append(test_df,sort=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "potential-telling",
   "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>Airline</th>\n",
       "      <th>Date_of_Journey</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2666</th>\n",
       "      <td>Air India</td>\n",
       "      <td>6/06/2019</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? DEL ? BLR</td>\n",
       "      <td>20:30</td>\n",
       "      <td>20:25 07 Jun</td>\n",
       "      <td>23h 55m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2667</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>27/03/2019</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? BLR</td>\n",
       "      <td>14:20</td>\n",
       "      <td>16:55</td>\n",
       "      <td>2h 35m</td>\n",
       "      <td>non-stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2668</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>6/03/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? BOM ? COK</td>\n",
       "      <td>21:50</td>\n",
       "      <td>04:25 07 Mar</td>\n",
       "      <td>6h 35m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2669</th>\n",
       "      <td>Air India</td>\n",
       "      <td>6/03/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? BOM ? COK</td>\n",
       "      <td>04:00</td>\n",
       "      <td>19:15</td>\n",
       "      <td>15h 15m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2670</th>\n",
       "      <td>Multiple carriers</td>\n",
       "      <td>15/06/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? BOM ? COK</td>\n",
       "      <td>04:55</td>\n",
       "      <td>19:15</td>\n",
       "      <td>14h 20m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Airline Date_of_Journey   Source Destination            Route  \\\n",
       "2666          Air India       6/06/2019  Kolkata    Banglore  CCU ? DEL ? BLR   \n",
       "2667             IndiGo      27/03/2019  Kolkata    Banglore        CCU ? BLR   \n",
       "2668        Jet Airways       6/03/2019    Delhi      Cochin  DEL ? BOM ? COK   \n",
       "2669          Air India       6/03/2019    Delhi      Cochin  DEL ? BOM ? COK   \n",
       "2670  Multiple carriers      15/06/2019    Delhi      Cochin  DEL ? BOM ? COK   \n",
       "\n",
       "     Dep_Time  Arrival_Time Duration Total_Stops Additional_Info  Price  \n",
       "2666    20:30  20:25 07 Jun  23h 55m      1 stop         No info    NaN  \n",
       "2667    14:20         16:55   2h 35m    non-stop         No info    NaN  \n",
       "2668    21:50  04:25 07 Mar   6h 35m      1 stop         No info    NaN  \n",
       "2669    04:00         19:15  15h 15m      1 stop         No info    NaN  \n",
       "2670    04:55         19:15  14h 20m      1 stop         No info    NaN  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "active-habitat",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Airline             object\n",
       "Date_of_Journey     object\n",
       "Source              object\n",
       "Destination         object\n",
       "Route               object\n",
       "Dep_Time            object\n",
       "Arrival_Time        object\n",
       "Duration            object\n",
       "Total_Stops         object\n",
       "Additional_Info     object\n",
       "Price              float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "round-copper",
   "metadata": {},
   "source": [
    "### Feature Engineering"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "arabic-plenty",
   "metadata": {},
   "source": [
    "#### Spliting 'Date_of_Journey' into 'Date','Month' and 'Year'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "monetary-warrior",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Date']=big_df['Date_of_Journey'].str.split('/').str[0]\n",
    "big_df['Month']=big_df['Date_of_Journey'].str.split('/').str[1]\n",
    "big_df['Year']=big_df['Date_of_Journey'].str.split('/').str[2]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "banned-version",
   "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>Airline</th>\n",
       "      <th>Date_of_Journey</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>24/03/2019</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>01:10 22 Mar</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>non-stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>03</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>1/05/2019</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>13:15</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>05</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>9/06/2019</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>04:25 10 Jun</td>\n",
       "      <td>19h</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>06</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>12/05/2019</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>23:30</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>05</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>01/03/2019</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>21:35</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>01</td>\n",
       "      <td>03</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline Date_of_Journey    Source Destination                  Route  \\\n",
       "0       IndiGo      24/03/2019  Banglore   New Delhi              BLR ? DEL   \n",
       "1    Air India       1/05/2019   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR   \n",
       "2  Jet Airways       9/06/2019     Delhi      Cochin  DEL ? LKO ? BOM ? COK   \n",
       "3       IndiGo      12/05/2019   Kolkata    Banglore        CCU ? NAG ? BLR   \n",
       "4       IndiGo      01/03/2019  Banglore   New Delhi        BLR ? NAG ? DEL   \n",
       "\n",
       "  Dep_Time  Arrival_Time Duration Total_Stops Additional_Info    Price Date  \\\n",
       "0    22:20  01:10 22 Mar   2h 50m    non-stop         No info   3897.0   24   \n",
       "1    05:50         13:15   7h 25m     2 stops         No info   7662.0    1   \n",
       "2    09:25  04:25 10 Jun      19h     2 stops         No info  13882.0    9   \n",
       "3    18:05         23:30   5h 25m      1 stop         No info   6218.0   12   \n",
       "4    16:50         21:35   4h 45m      1 stop         No info  13302.0   01   \n",
       "\n",
       "  Month  Year  \n",
       "0    03  2019  \n",
       "1    05  2019  \n",
       "2    06  2019  \n",
       "3    05  2019  \n",
       "4    03  2019  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "furnished-selling",
   "metadata": {},
   "source": [
    "#### Converting 'Date','Month' and 'Year' into int."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "drawn-blogger",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Date']=big_df['Date'].astype('int')\n",
    "big_df['Month']=big_df['Month'].astype('int')\n",
    "big_df['Year']=big_df['Year'].astype('int')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "subjective-weekly",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Airline             object\n",
       "Date_of_Journey     object\n",
       "Source              object\n",
       "Destination         object\n",
       "Route               object\n",
       "Dep_Time            object\n",
       "Arrival_Time        object\n",
       "Duration            object\n",
       "Total_Stops         object\n",
       "Additional_Info     object\n",
       "Price              float64\n",
       "Date                 int32\n",
       "Month                int32\n",
       "Year                 int32\n",
       "dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cooked-bread",
   "metadata": {},
   "source": [
    "#### Dropping 'Date_of_Journey'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "complex-taiwan",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df=big_df.drop(['Date_of_Journey'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "rotary-keyboard",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>01:10 22 Mar</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>non-stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>13:15</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>04:25 10 Jun</td>\n",
       "      <td>19h</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>23:30</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>21:35</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Dep_Time  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL    22:20   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR    05:50   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK    09:25   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR    18:05   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL    16:50   \n",
       "\n",
       "   Arrival_Time Duration Total_Stops Additional_Info    Price  Date  Month  \\\n",
       "0  01:10 22 Mar   2h 50m    non-stop         No info   3897.0    24      3   \n",
       "1         13:15   7h 25m     2 stops         No info   7662.0     1      5   \n",
       "2  04:25 10 Jun      19h     2 stops         No info  13882.0     9      6   \n",
       "3         23:30   5h 25m      1 stop         No info   6218.0    12      5   \n",
       "4         21:35   4h 45m      1 stop         No info  13302.0     1      3   \n",
       "\n",
       "   Year  \n",
       "0  2019  \n",
       "1  2019  \n",
       "2  2019  \n",
       "3  2019  \n",
       "4  2019  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "warming-fitness",
   "metadata": {},
   "source": [
    "#### Spliting 'Arrival_Time'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "killing-doubt",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Arrival_Time']=big_df['Arrival_Time'].str.split(' ').str[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "fifth-backing",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>01:10</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>non-stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>13:15</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>04:25</td>\n",
       "      <td>19h</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>23:30</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>21:35</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Dep_Time  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL    22:20   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR    05:50   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK    09:25   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR    18:05   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL    16:50   \n",
       "\n",
       "  Arrival_Time Duration Total_Stops Additional_Info    Price  Date  Month  \\\n",
       "0        01:10   2h 50m    non-stop         No info   3897.0    24      3   \n",
       "1        13:15   7h 25m     2 stops         No info   7662.0     1      5   \n",
       "2        04:25      19h     2 stops         No info  13882.0     9      6   \n",
       "3        23:30   5h 25m      1 stop         No info   6218.0    12      5   \n",
       "4        21:35   4h 45m      1 stop         No info  13302.0     1      3   \n",
       "\n",
       "   Year  \n",
       "0  2019  \n",
       "1  2019  \n",
       "2  2019  \n",
       "3  2019  \n",
       "4  2019  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "small-checklist",
   "metadata": {},
   "source": [
    "#### Filling NaN values of 'Total_Stops'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "polished-horror",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Airline               0\n",
       "Source                0\n",
       "Destination           0\n",
       "Route                 1\n",
       "Dep_Time              0\n",
       "Arrival_Time          0\n",
       "Duration              0\n",
       "Total_Stops           1\n",
       "Additional_Info       0\n",
       "Price              2671\n",
       "Date                  0\n",
       "Month                 0\n",
       "Year                  0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "fewer-russell",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9039</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>NaN</td>\n",
       "      <td>09:45</td>\n",
       "      <td>09:25</td>\n",
       "      <td>23h 40m</td>\n",
       "      <td>NaN</td>\n",
       "      <td>No info</td>\n",
       "      <td>7480.0</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Airline Source Destination Route Dep_Time Arrival_Time Duration  \\\n",
       "9039  Air India  Delhi      Cochin   NaN    09:45        09:25  23h 40m   \n",
       "\n",
       "     Total_Stops Additional_Info   Price  Date  Month  Year  \n",
       "9039         NaN         No info  7480.0     6      5  2019  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df[big_df['Total_Stops'].isnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "little-mortality",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Total_Stops']=big_df['Total_Stops'].fillna('1 stop')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "valuable-evolution",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Airline               0\n",
       "Source                0\n",
       "Destination           0\n",
       "Route                 1\n",
       "Dep_Time              0\n",
       "Arrival_Time          0\n",
       "Duration              0\n",
       "Total_Stops           0\n",
       "Additional_Info       0\n",
       "Price              2671\n",
       "Date                  0\n",
       "Month                 0\n",
       "Year                  0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "burning-harrison",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Airline, Source, Destination, Route, Dep_Time, Arrival_Time, Duration, Total_Stops, Additional_Info, Price, Date, Month, Year]\n",
       "Index: []"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df[big_df['Total_Stops'].isnull()]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "trying-friendship",
   "metadata": {},
   "source": [
    "#### Replacing 'non stop'with '0 stop'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "worth-amber",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Total_Stops']=big_df['Total_Stops'].replace('non-stop','0 stop')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "local-petite",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>01:10</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>0 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>13:15</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>04:25</td>\n",
       "      <td>19h</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>23:30</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>21:35</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Dep_Time  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL    22:20   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR    05:50   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK    09:25   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR    18:05   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL    16:50   \n",
       "\n",
       "  Arrival_Time Duration Total_Stops Additional_Info    Price  Date  Month  \\\n",
       "0        01:10   2h 50m      0 stop         No info   3897.0    24      3   \n",
       "1        13:15   7h 25m     2 stops         No info   7662.0     1      5   \n",
       "2        04:25      19h     2 stops         No info  13882.0     9      6   \n",
       "3        23:30   5h 25m      1 stop         No info   6218.0    12      5   \n",
       "4        21:35   4h 45m      1 stop         No info  13302.0     1      3   \n",
       "\n",
       "   Year  \n",
       "0  2019  \n",
       "1  2019  \n",
       "2  2019  \n",
       "3  2019  \n",
       "4  2019  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "contrary-topic",
   "metadata": {},
   "source": [
    "#### Spliting 'Total_Stops' and converting into int and dropping."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "signal-bridge",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Stop']=big_df['Total_Stops'].str.split(' ').str[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "mediterranean-graham",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Total_Stops</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "      <th>Stop</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>01:10</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>0 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>13:15</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>04:25</td>\n",
       "      <td>19h</td>\n",
       "      <td>2 stops</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>23:30</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>21:35</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>1 stop</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Dep_Time  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL    22:20   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR    05:50   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK    09:25   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR    18:05   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL    16:50   \n",
       "\n",
       "  Arrival_Time Duration Total_Stops Additional_Info    Price  Date  Month  \\\n",
       "0        01:10   2h 50m      0 stop         No info   3897.0    24      3   \n",
       "1        13:15   7h 25m     2 stops         No info   7662.0     1      5   \n",
       "2        04:25      19h     2 stops         No info  13882.0     9      6   \n",
       "3        23:30   5h 25m      1 stop         No info   6218.0    12      5   \n",
       "4        21:35   4h 45m      1 stop         No info  13302.0     1      3   \n",
       "\n",
       "   Year Stop  \n",
       "0  2019    0  \n",
       "1  2019    2  \n",
       "2  2019    2  \n",
       "3  2019    1  \n",
       "4  2019    1  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "balanced-geneva",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Airline             object\n",
       "Source              object\n",
       "Destination         object\n",
       "Route               object\n",
       "Dep_Time            object\n",
       "Arrival_Time        object\n",
       "Duration            object\n",
       "Total_Stops         object\n",
       "Additional_Info     object\n",
       "Price              float64\n",
       "Date                 int32\n",
       "Month                int32\n",
       "Year                 int32\n",
       "Stop                object\n",
       "dtype: object"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "subtle-environment",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Stop']=big_df['Stop'].astype('int')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "present-operation",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df=big_df.drop(['Total_Stops'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "unavailable-listing",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Arrival_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "      <th>Stop</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>01:10</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>13:15</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>04:25</td>\n",
       "      <td>19h</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>23:30</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>21:35</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Dep_Time  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL    22:20   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR    05:50   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK    09:25   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR    18:05   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL    16:50   \n",
       "\n",
       "  Arrival_Time Duration Additional_Info    Price  Date  Month  Year  Stop  \n",
       "0        01:10   2h 50m         No info   3897.0    24      3  2019     0  \n",
       "1        13:15   7h 25m         No info   7662.0     1      5  2019     2  \n",
       "2        04:25      19h         No info  13882.0     9      6  2019     2  \n",
       "3        23:30   5h 25m         No info   6218.0    12      5  2019     1  \n",
       "4        21:35   4h 45m         No info  13302.0     1      3  2019     1  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "direct-contractor",
   "metadata": {},
   "source": [
    "#### Spliting 'Arrival_Time'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "tight-criminal",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Arrival_Hour'] = big_df['Arrival_Time'] .str.split(':').str[0]\n",
    "big_df['Arrival_Minute'] = big_df['Arrival_Time'] .str.split(':').str[1]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "preceding-settlement",
   "metadata": {},
   "source": [
    "#### Converting to int and dropping 'Arrival_Time'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "billion-element",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Arrival_Hour']=big_df['Arrival_Hour'].astype(int)\n",
    "big_df['Arrival_Minute']=big_df['Arrival_Minute'].astype(int)\n",
    "big_df=big_df.drop(['Arrival_Time'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "threaded-croatia",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Dep_Time</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "      <th>Stop</th>\n",
       "      <th>Arrival_Hour</th>\n",
       "      <th>Arrival_Minute</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>22:20</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>05:50</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>09:25</td>\n",
       "      <td>19h</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>18:05</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>16:50</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>21</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Dep_Time Duration  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL    22:20   2h 50m   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR    05:50   7h 25m   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK    09:25      19h   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR    18:05   5h 25m   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL    16:50   4h 45m   \n",
       "\n",
       "  Additional_Info    Price  Date  Month  Year  Stop  Arrival_Hour  \\\n",
       "0         No info   3897.0    24      3  2019     0             1   \n",
       "1         No info   7662.0     1      5  2019     2            13   \n",
       "2         No info  13882.0     9      6  2019     2             4   \n",
       "3         No info   6218.0    12      5  2019     1            23   \n",
       "4         No info  13302.0     1      3  2019     1            21   \n",
       "\n",
       "   Arrival_Minute  \n",
       "0              10  \n",
       "1              15  \n",
       "2              25  \n",
       "3              30  \n",
       "4              35  "
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "patent-missouri",
   "metadata": {},
   "source": [
    "#### Spliting 'Dep_Time'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "uniform-symposium",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Departure_Hour'] = big_df['Dep_Time'] .str.split(':').str[0]\n",
    "big_df['Departure_Minute'] = big_df['Dep_Time'] .str.split(':').str[1]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "absent-protocol",
   "metadata": {},
   "source": [
    "#### Converting to int and dropping 'Dep_Time'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "arranged-ghost",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Departure_Hour']=big_df['Departure_Hour'].astype(int)\n",
    "big_df['Departure_Minute']=big_df['Departure_Minute'].astype(int)\n",
    "big_df=big_df.drop(['Dep_Time'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "sharp-subcommittee",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "      <th>Stop</th>\n",
       "      <th>Arrival_Hour</th>\n",
       "      <th>Arrival_Minute</th>\n",
       "      <th>Departure_Hour</th>\n",
       "      <th>Departure_Minute</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>19h</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>25</td>\n",
       "      <td>9</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "      <td>18</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>21</td>\n",
       "      <td>35</td>\n",
       "      <td>16</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Duration  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL   2h 50m   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR   7h 25m   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK      19h   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR   5h 25m   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL   4h 45m   \n",
       "\n",
       "  Additional_Info    Price  Date  Month  Year  Stop  Arrival_Hour  \\\n",
       "0         No info   3897.0    24      3  2019     0             1   \n",
       "1         No info   7662.0     1      5  2019     2            13   \n",
       "2         No info  13882.0     9      6  2019     2             4   \n",
       "3         No info   6218.0    12      5  2019     1            23   \n",
       "4         No info  13302.0     1      3  2019     1            21   \n",
       "\n",
       "   Arrival_Minute  Departure_Hour  Departure_Minute  \n",
       "0              10              22                20  \n",
       "1              15               5                50  \n",
       "2              25               9                25  \n",
       "3              30              18                 5  \n",
       "4              35              16                50  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "mobile-pocket",
   "metadata": {},
   "source": [
    "#### Spliting 'Route'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "solid-victim",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Route_1']=big_df['Route'].str.split('?').str[0]\n",
    "big_df['Route_2']=big_df['Route'].str.split('?').str[1]\n",
    "big_df['Route_3']=big_df['Route'].str.split('?').str[2]\n",
    "big_df['Route_4']=big_df['Route'].str.split('?').str[3]\n",
    "big_df['Route_5']=big_df['Route'].str.split('?').str[4]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "conditional-instrument",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Route</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "      <th>Stop</th>\n",
       "      <th>Arrival_Hour</th>\n",
       "      <th>Arrival_Minute</th>\n",
       "      <th>Departure_Hour</th>\n",
       "      <th>Departure_Minute</th>\n",
       "      <th>Route_1</th>\n",
       "      <th>Route_2</th>\n",
       "      <th>Route_3</th>\n",
       "      <th>Route_4</th>\n",
       "      <th>Route_5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? DEL</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "      <td>20</td>\n",
       "      <td>BLR</td>\n",
       "      <td>DEL</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? IXR ? BBI ? BLR</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>50</td>\n",
       "      <td>CCU</td>\n",
       "      <td>IXR</td>\n",
       "      <td>BBI</td>\n",
       "      <td>BLR</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>DEL ? LKO ? BOM ? COK</td>\n",
       "      <td>19h</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>25</td>\n",
       "      <td>9</td>\n",
       "      <td>25</td>\n",
       "      <td>DEL</td>\n",
       "      <td>LKO</td>\n",
       "      <td>BOM</td>\n",
       "      <td>COK</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>CCU ? NAG ? BLR</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "      <td>18</td>\n",
       "      <td>5</td>\n",
       "      <td>CCU</td>\n",
       "      <td>NAG</td>\n",
       "      <td>BLR</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>BLR ? NAG ? DEL</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>21</td>\n",
       "      <td>35</td>\n",
       "      <td>16</td>\n",
       "      <td>50</td>\n",
       "      <td>BLR</td>\n",
       "      <td>NAG</td>\n",
       "      <td>DEL</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination                  Route Duration  \\\n",
       "0       IndiGo  Banglore   New Delhi              BLR ? DEL   2h 50m   \n",
       "1    Air India   Kolkata    Banglore  CCU ? IXR ? BBI ? BLR   7h 25m   \n",
       "2  Jet Airways     Delhi      Cochin  DEL ? LKO ? BOM ? COK      19h   \n",
       "3       IndiGo   Kolkata    Banglore        CCU ? NAG ? BLR   5h 25m   \n",
       "4       IndiGo  Banglore   New Delhi        BLR ? NAG ? DEL   4h 45m   \n",
       "\n",
       "  Additional_Info    Price  Date  Month  Year  Stop  Arrival_Hour  \\\n",
       "0         No info   3897.0    24      3  2019     0             1   \n",
       "1         No info   7662.0     1      5  2019     2            13   \n",
       "2         No info  13882.0     9      6  2019     2             4   \n",
       "3         No info   6218.0    12      5  2019     1            23   \n",
       "4         No info  13302.0     1      3  2019     1            21   \n",
       "\n",
       "   Arrival_Minute  Departure_Hour  Departure_Minute Route_1 Route_2 Route_3  \\\n",
       "0              10              22                20    BLR      DEL     NaN   \n",
       "1              15               5                50    CCU     IXR     BBI    \n",
       "2              25               9                25    DEL     LKO     BOM    \n",
       "3              30              18                 5    CCU     NAG      BLR   \n",
       "4              35              16                50    BLR     NAG      DEL   \n",
       "\n",
       "  Route_4 Route_5  \n",
       "0     NaN     NaN  \n",
       "1     BLR     NaN  \n",
       "2     COK     NaN  \n",
       "3     NaN     NaN  \n",
       "4     NaN     NaN  "
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dominican-allowance",
   "metadata": {},
   "source": [
    "#### Filing 'NaN' with 'None'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "undefined-symbol",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Route_1'].fillna(\"None\",inplace=True)\n",
    "big_df['Route_2'].fillna(\"None\",inplace=True)\n",
    "big_df['Route_3'].fillna(\"None\",inplace=True)\n",
    "big_df['Route_4'].fillna(\"None\",inplace=True)\n",
    "big_df['Route_5'].fillna(\"None\",inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "victorian-funeral",
   "metadata": {},
   "source": [
    "#### Droping 'Route'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "freelance-cleaner",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df=big_df.drop(['Route'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "minor-albert",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Duration</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "      <th>Stop</th>\n",
       "      <th>Arrival_Hour</th>\n",
       "      <th>Arrival_Minute</th>\n",
       "      <th>Departure_Hour</th>\n",
       "      <th>Departure_Minute</th>\n",
       "      <th>Route_1</th>\n",
       "      <th>Route_2</th>\n",
       "      <th>Route_3</th>\n",
       "      <th>Route_4</th>\n",
       "      <th>Route_5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>2h 50m</td>\n",
       "      <td>No info</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "      <td>20</td>\n",
       "      <td>BLR</td>\n",
       "      <td>DEL</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Air India</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>7h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>50</td>\n",
       "      <td>CCU</td>\n",
       "      <td>IXR</td>\n",
       "      <td>BBI</td>\n",
       "      <td>BLR</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jet Airways</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Cochin</td>\n",
       "      <td>19h</td>\n",
       "      <td>No info</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>25</td>\n",
       "      <td>9</td>\n",
       "      <td>25</td>\n",
       "      <td>DEL</td>\n",
       "      <td>LKO</td>\n",
       "      <td>BOM</td>\n",
       "      <td>COK</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>5h 25m</td>\n",
       "      <td>No info</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "      <td>18</td>\n",
       "      <td>5</td>\n",
       "      <td>CCU</td>\n",
       "      <td>NAG</td>\n",
       "      <td>BLR</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IndiGo</td>\n",
       "      <td>Banglore</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>4h 45m</td>\n",
       "      <td>No info</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>21</td>\n",
       "      <td>35</td>\n",
       "      <td>16</td>\n",
       "      <td>50</td>\n",
       "      <td>BLR</td>\n",
       "      <td>NAG</td>\n",
       "      <td>DEL</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Airline    Source Destination Duration Additional_Info    Price  Date  \\\n",
       "0       IndiGo  Banglore   New Delhi   2h 50m         No info   3897.0    24   \n",
       "1    Air India   Kolkata    Banglore   7h 25m         No info   7662.0     1   \n",
       "2  Jet Airways     Delhi      Cochin      19h         No info  13882.0     9   \n",
       "3       IndiGo   Kolkata    Banglore   5h 25m         No info   6218.0    12   \n",
       "4       IndiGo  Banglore   New Delhi   4h 45m         No info  13302.0     1   \n",
       "\n",
       "   Month  Year  Stop  Arrival_Hour  Arrival_Minute  Departure_Hour  \\\n",
       "0      3  2019     0             1              10              22   \n",
       "1      5  2019     2            13              15               5   \n",
       "2      6  2019     2             4              25               9   \n",
       "3      5  2019     1            23              30              18   \n",
       "4      3  2019     1            21              35              16   \n",
       "\n",
       "   Departure_Minute Route_1 Route_2 Route_3 Route_4 Route_5  \n",
       "0                20    BLR      DEL    None    None    None  \n",
       "1                50    CCU     IXR     BBI      BLR    None  \n",
       "2                25    DEL     LKO     BOM      COK    None  \n",
       "3                 5    CCU     NAG      BLR    None    None  \n",
       "4                50    BLR     NAG      DEL    None    None  "
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "enabling-space",
   "metadata": {},
   "source": [
    "#### Filling 'NaN' values with mean for 'Price' "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "sized-latest",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Price'].fillna((big_df['Price'].mean()),inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "grave-kelly",
   "metadata": {},
   "source": [
    "#### Droping 'Duration'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "specialized-cooperative",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df=big_df.drop(['Duration'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "scenic-palmer",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Airline             0\n",
       "Source              0\n",
       "Destination         0\n",
       "Additional_Info     0\n",
       "Price               0\n",
       "Date                0\n",
       "Month               0\n",
       "Year                0\n",
       "Stop                0\n",
       "Arrival_Hour        0\n",
       "Arrival_Minute      0\n",
       "Departure_Hour      0\n",
       "Departure_Minute    0\n",
       "Route_1             0\n",
       "Route_2             0\n",
       "Route_3             0\n",
       "Route_4             0\n",
       "Route_5             0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "homeless-bench",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Airline              object\n",
       "Source               object\n",
       "Destination          object\n",
       "Additional_Info      object\n",
       "Price               float64\n",
       "Date                  int32\n",
       "Month                 int32\n",
       "Year                  int32\n",
       "Stop                  int32\n",
       "Arrival_Hour          int32\n",
       "Arrival_Minute        int32\n",
       "Departure_Hour        int32\n",
       "Departure_Minute      int32\n",
       "Route_1              object\n",
       "Route_2              object\n",
       "Route_3              object\n",
       "Route_4              object\n",
       "Route_5              object\n",
       "dtype: object"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "alone-mechanics",
   "metadata": {},
   "source": [
    "##### Label Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "choice-therapist",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import LabelEncoder\n",
    "encoder=LabelEncoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "lined-triple",
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df['Airline']=encoder.fit_transform(big_df['Airline'])\n",
    "big_df[\"Source\"]=encoder.fit_transform(big_df['Source'])\n",
    "big_df[\"Destination\"]=encoder.fit_transform(big_df['Destination'])\n",
    "big_df[\"Additional_Info\"]=encoder.fit_transform(big_df['Additional_Info'])\n",
    "big_df[\"Route_1\"]=encoder.fit_transform(big_df['Route_1'])\n",
    "big_df[\"Route_2\"]=encoder.fit_transform(big_df['Route_2'])\n",
    "big_df[\"Route_3\"]=encoder.fit_transform(big_df['Route_3'])\n",
    "big_df[\"Route_4\"]=encoder.fit_transform(big_df['Route_4'])\n",
    "big_df[\"Route_5\"]=encoder.fit_transform(big_df['Route_5'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "affiliated-savage",
   "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>Airline</th>\n",
       "      <th>Source</th>\n",
       "      <th>Destination</th>\n",
       "      <th>Additional_Info</th>\n",
       "      <th>Price</th>\n",
       "      <th>Date</th>\n",
       "      <th>Month</th>\n",
       "      <th>Year</th>\n",
       "      <th>Stop</th>\n",
       "      <th>Arrival_Hour</th>\n",
       "      <th>Arrival_Minute</th>\n",
       "      <th>Departure_Hour</th>\n",
       "      <th>Departure_Minute</th>\n",
       "      <th>Route_1</th>\n",
       "      <th>Route_2</th>\n",
       "      <th>Route_3</th>\n",
       "      <th>Route_4</th>\n",
       "      <th>Route_5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>8</td>\n",
       "      <td>3897.0</td>\n",
       "      <td>24</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>22</td>\n",
       "      <td>20</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>30</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>7662.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>50</td>\n",
       "      <td>2</td>\n",
       "      <td>25</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>13882.0</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>2019</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>25</td>\n",
       "      <td>9</td>\n",
       "      <td>25</td>\n",
       "      <td>3</td>\n",
       "      <td>32</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>6218.0</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "      <td>18</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>34</td>\n",
       "      <td>3</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>8</td>\n",
       "      <td>13302.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2019</td>\n",
       "      <td>1</td>\n",
       "      <td>21</td>\n",
       "      <td>35</td>\n",
       "      <td>16</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>8</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Airline  Source  Destination  Additional_Info    Price  Date  Month  Year  \\\n",
       "0        3       0            5                8   3897.0    24      3  2019   \n",
       "1        1       3            0                8   7662.0     1      5  2019   \n",
       "2        4       2            1                8  13882.0     9      6  2019   \n",
       "3        3       3            0                8   6218.0    12      5  2019   \n",
       "4        3       0            5                8  13302.0     1      3  2019   \n",
       "\n",
       "   Stop  Arrival_Hour  Arrival_Minute  Departure_Hour  Departure_Minute  \\\n",
       "0     0             1              10              22                20   \n",
       "1     2            13              15               5                50   \n",
       "2     2             4              25               9                25   \n",
       "3     1            23              30              18                 5   \n",
       "4     1            21              35              16                50   \n",
       "\n",
       "   Route_1  Route_2  Route_3  Route_4  Route_5  \n",
       "0        0       13       30       13        5  \n",
       "1        2       25        1        3        5  \n",
       "2        3       32        4        5        5  \n",
       "3        2       34        3       13        5  \n",
       "4        0       34        8       13        5  "
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "expired-county",
   "metadata": {},
   "source": [
    "### Feature Selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "billion-invention",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import Lasso\n",
    "from sklearn.feature_selection import SelectFromModel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "covered-strength",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train=big_df[0:10683]\n",
    "df_test=big_df[10683:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "separated-forge",
   "metadata": {},
   "outputs": [],
   "source": [
    "X=df_train.drop(['Price'],axis=1)\n",
    "y=df_train['Price']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "wireless-score",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "emotional-kernel",
   "metadata": {},
   "outputs": [],
   "source": [
    "model=SelectFromModel(Lasso(alpha=0.005,random_state=0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "geological-worry",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SelectFromModel(estimator=Lasso(alpha=0.005, random_state=0))"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "collected-pitch",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ True,  True,  True,  True,  True,  True, False,  True,  True,\n",
       "        True,  True,  True,  True,  True,  True,  True,  True])"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.get_support()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "parallel-accused",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_features=X_train.columns[(model.get_support())]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "daily-campaign",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Airline', 'Source', 'Destination', 'Additional_Info', 'Date', 'Month',\n",
       "       'Stop', 'Arrival_Hour', 'Arrival_Minute', 'Departure_Hour',\n",
       "       'Departure_Minute', 'Route_1', 'Route_2', 'Route_3', 'Route_4',\n",
       "       'Route_5'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "subsequent-protein",
   "metadata": {},
   "source": [
    "##### Dropping the 'Year' feature since it is not that important here"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "mexican-automation",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train=X_train.drop(['Year'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "acute-prison",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test=X_test.drop(['Year'],axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "partial-worcester",
   "metadata": {},
   "source": [
    "### RandomForestRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "possible-hammer",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "#Randomized Search CV\n",
    "\n",
    "# Number of trees in random forest\n",
    "n_estimators = [int(x) for x in np.linspace(start = 100, stop = 1200, num = 12)]\n",
    "# Number of features to consider at every split\n",
    "max_features = ['auto', 'sqrt']\n",
    "# Maximum number of levels in tree\n",
    "max_depth = [int(x) for x in np.linspace(5, 30, num = 6)]\n",
    "# max_depth.append(None)\n",
    "# Minimum number of samples required to split a node\n",
    "min_samples_split = [2, 5, 10, 15, 100]\n",
    "# Minimum number of samples required at each leaf node\n",
    "min_samples_leaf = [1, 2, 5, 10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "available-treatment",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'n_estimators': [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200], 'max_features': ['auto', 'sqrt'], 'max_depth': [5, 10, 15, 20, 25, 30], 'min_samples_split': [2, 5, 10, 15, 100], 'min_samples_leaf': [1, 2, 5, 10]}\n"
     ]
    }
   ],
   "source": [
    "# Create the random grid\n",
    "random_grid = {'n_estimators': n_estimators,\n",
    "               'max_features': max_features,\n",
    "               'max_depth': max_depth,\n",
    "               'min_samples_split': min_samples_split,\n",
    "               'min_samples_leaf': min_samples_leaf}\n",
    "\n",
    "print(random_grid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "polar-norway",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use the random grid to search for best hyperparameters\n",
    "# First create the base model to tune\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "rf = RandomForestRegressor()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "valid-stereo",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Random search of parameters, using 3 fold cross validation, \n",
    "# search across 50 different combinations\n",
    "rf_random = RandomizedSearchCV(estimator = rf, param_distributions = random_grid,scoring='neg_mean_squared_error', n_iter = 50, cv = 5, verbose=2, random_state=42, n_jobs = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "hispanic-twelve",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 50 candidates, totalling 250 fits\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=400; total time=   3.7s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=400; total time=   3.3s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=400; total time=   3.3s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=400; total time=   3.8s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=400; total time=   4.2s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   7.6s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   7.2s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   7.2s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   7.7s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   7.2s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=200; total time=   2.6s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=200; total time=   2.9s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=200; total time=   2.9s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=200; total time=   2.8s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=600; total time=  23.3s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=600; total time=  21.4s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=600; total time=  21.5s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=600; total time=  21.4s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=600; total time=  22.4s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=  10.7s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=  11.1s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=  12.2s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=  15.8s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=  13.7s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=800; total time=  12.8s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=800; total time=  12.5s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=800; total time=   8.4s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=800; total time=   8.4s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=800; total time=   8.5s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=100, n_estimators=100; total time=   2.2s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=100, n_estimators=100; total time=   2.1s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=100, n_estimators=100; total time=   2.0s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=100, n_estimators=100; total time=   2.1s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=5, min_samples_split=100, n_estimators=100; total time=   2.3s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=900; total time=  15.4s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=900; total time=  12.6s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=900; total time=  12.4s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=900; total time=  12.5s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=900; total time=  12.3s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=1000; total time=  10.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=1000; total time=  10.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=1000; total time=  10.9s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=1000; total time=  10.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=15, n_estimators=1000; total time=  10.8s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=100; total time=   1.2s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=100; total time=   1.2s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=100; total time=   1.2s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=100; total time=   1.2s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=100; total time=   1.2s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=   3.8s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=   3.8s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=   3.8s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=   3.8s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=300; total time=   3.8s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time=   5.4s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time=   5.4s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time=   5.5s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time=   5.6s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time=   5.4s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=900; total time=   7.4s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=900; total time=   7.4s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=900; total time=   7.6s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=900; total time=   7.4s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=900; total time=   7.4s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=900; total time=  13.8s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=900; total time=  13.9s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=900; total time=  13.9s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=900; total time=  14.6s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=900; total time=  14.0s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=200; total time=   2.2s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=200; total time=   2.2s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=200; total time=   2.2s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time=   2.3s\n",
      "[CV] END max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=700; total time=  17.8s\n",
      "[CV] END max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=700; total time=  18.0s\n",
      "[CV] END max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=700; total time=  18.3s\n",
      "[CV] END max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=700; total time=  18.0s\n",
      "[CV] END max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=700; total time=  17.9s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=10, min_samples_split=100, n_estimators=1200; total time=  18.8s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=10, min_samples_split=100, n_estimators=1200; total time=  18.6s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=10, min_samples_split=100, n_estimators=1200; total time=  18.7s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=10, min_samples_split=100, n_estimators=1200; total time=  18.7s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=10, min_samples_split=100, n_estimators=1200; total time=  18.7s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time=   6.6s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time=   6.5s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time=   6.6s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time=   6.6s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time=   6.7s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=1100; total time=  10.9s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=1100; total time=  10.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=1100; total time=  10.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=1100; total time=  10.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=1100; total time=  10.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=500; total time=   4.9s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=500; total time=   4.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=500; total time=   5.0s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=500; total time=   4.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=500; total time=   4.8s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time=  15.1s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time=  14.9s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time=  15.0s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time=  15.4s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time=  14.9s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time=  14.7s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time=  15.6s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time=  15.6s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time=  15.1s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time=  15.0s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time=  13.9s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time=  13.9s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time=  17.3s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time=  18.6s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time=  18.7s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=300; total time=   5.0s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=300; total time=   5.1s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=300; total time=   5.1s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=300; total time=   5.6s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=15, n_estimators=300; total time=   5.8s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time=  26.8s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time=  26.2s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time=  26.7s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time=  26.1s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time=  26.5s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1100; total time=  47.8s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1100; total time=  48.9s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1100; total time=  50.9s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1100; total time=  49.3s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1100; total time=  48.8s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=100, n_estimators=300; total time=   8.4s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=100, n_estimators=300; total time=   8.5s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=100, n_estimators=300; total time=   8.8s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=100, n_estimators=300; total time=   8.6s\n",
      "[CV] END max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=100, n_estimators=300; total time=   8.8s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=100; total time=   1.9s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=100; total time=   2.0s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=100; total time=   2.1s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=100; total time=   1.9s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=100; total time=   1.9s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=700; total time=   9.1s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=700; total time=   9.1s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=700; total time=   9.3s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=700; total time=   9.0s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=700; total time=   8.9s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=200; total time=   2.5s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=200; total time=   2.5s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=200; total time=   2.5s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=200; total time=   2.5s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=100, n_estimators=200; total time=   2.5s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  18.2s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  18.3s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  20.4s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  18.9s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  18.9s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=900; total time=  13.5s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=900; total time=  14.0s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=900; total time=  14.0s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=900; total time=  13.7s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=900; total time=  13.9s\n",
      "[CV] END max_depth=30, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=1200; total time=  42.6s\n",
      "[CV] END max_depth=30, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=1200; total time=  42.8s\n",
      "[CV] END max_depth=30, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=1200; total time=  43.9s\n",
      "[CV] END max_depth=30, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=1200; total time=  44.6s\n",
      "[CV] END max_depth=30, max_features=auto, min_samples_leaf=5, min_samples_split=15, n_estimators=1200; total time=  49.2s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  35.5s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  31.8s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  38.1s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  36.8s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  37.1s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=600; total time=   9.1s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=600; total time=   8.8s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=600; total time=   8.9s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=600; total time=   9.0s\n",
      "[CV] END max_depth=10, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=600; total time=   9.5s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=800; total time=  13.7s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=800; total time=  14.0s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=800; total time=  13.7s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=800; total time=  13.6s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=5, min_samples_split=5, n_estimators=800; total time=  14.1s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  10.4s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  10.7s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  10.5s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  10.6s\n",
      "[CV] END max_depth=5, max_features=auto, min_samples_leaf=5, min_samples_split=2, n_estimators=500; total time=  10.4s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=800; total time=  11.1s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=800; total time=  10.6s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=800; total time=  11.1s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=800; total time=  11.0s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=2, min_samples_split=100, n_estimators=800; total time=  11.0s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=1200; total time=  20.5s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=1200; total time=  21.4s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=1200; total time=  21.0s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=1200; total time=  20.2s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=1200; total time=  20.3s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time=  11.1s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time=  10.8s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time=  10.8s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time=  11.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time=  13.3s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  37.9s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  37.5s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  38.2s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  37.1s\n",
      "[CV] END max_depth=20, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=900; total time=  36.4s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=200; total time=   3.5s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=200; total time=   3.4s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=200; total time=   3.2s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=200; total time=   3.2s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=200; total time=   3.2s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=700; total time=  10.5s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=700; total time=  10.7s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=700; total time=  11.3s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=700; total time=  10.9s\n",
      "[CV] END max_depth=25, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=700; total time=  10.9s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time=   3.8s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time=   4.2s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time=   2.9s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time=   2.9s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time=   2.9s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=100, n_estimators=200; total time=   5.5s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=100, n_estimators=200; total time=   6.4s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=100, n_estimators=200; total time=   5.9s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=100, n_estimators=200; total time=   7.4s\n",
      "[CV] END max_depth=25, max_features=auto, min_samples_leaf=2, min_samples_split=100, n_estimators=200; total time=   5.8s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=400; total time=   6.9s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=400; total time=   7.0s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=400; total time=   8.2s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=400; total time=   6.3s\n",
      "[CV] END max_depth=20, max_features=sqrt, min_samples_leaf=5, min_samples_split=2, n_estimators=400; total time=   5.4s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=   8.0s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=   7.9s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=   8.1s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=  10.6s\n",
      "[CV] END max_depth=5, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=  10.0s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=  12.4s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=  12.3s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=  12.6s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=  12.4s\n",
      "[CV] END max_depth=30, max_features=sqrt, min_samples_leaf=1, min_samples_split=100, n_estimators=900; total time=  12.4s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   4.0s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   4.1s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   4.4s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   4.3s\n",
      "[CV] END max_depth=15, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time=   4.6s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "RandomizedSearchCV(cv=5, estimator=RandomForestRegressor(), n_iter=50, n_jobs=1,\n",
       "                   param_distributions={'max_depth': [5, 10, 15, 20, 25, 30],\n",
       "                                        'max_features': ['auto', 'sqrt'],\n",
       "                                        'min_samples_leaf': [1, 2, 5, 10],\n",
       "                                        'min_samples_split': [2, 5, 10, 15,\n",
       "                                                              100],\n",
       "                                        'n_estimators': [100, 200, 300, 400,\n",
       "                                                         500, 600, 700, 800,\n",
       "                                                         900, 1000, 1100,\n",
       "                                                         1200]},\n",
       "                   random_state=42, scoring='neg_mean_squared_error',\n",
       "                   verbose=2)"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_random.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "approximate-watts",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred=rf_random.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "medium-sound",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\swarnava\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\seaborn\\distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Price', ylabel='Density'>"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "\n",
    "sns.distplot(y_test-y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "greek-example",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x22bdeb92ac8>"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "commercial-measurement",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}