Tariq Fitria Aziz_Final Project.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Final Project - Intermediate Python AI Mentorship"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## DATA : Air BnB"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 1: Import Numpy, Pandas, and Matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 197,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib as mpl\n",
    "from matplotlib import pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 2: Import DataFrame File"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 219,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2539</td>\n",
       "      <td>Clean &amp; quiet apt home by the park</td>\n",
       "      <td>2787</td>\n",
       "      <td>John</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>40.64749</td>\n",
       "      <td>-73.97237</td>\n",
       "      <td>Private room</td>\n",
       "      <td>149</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-10-19</td>\n",
       "      <td>0.21</td>\n",
       "      <td>6</td>\n",
       "      <td>365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2595</td>\n",
       "      <td>Skylit Midtown Castle</td>\n",
       "      <td>2845</td>\n",
       "      <td>Jennifer</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Midtown</td>\n",
       "      <td>40.75362</td>\n",
       "      <td>-73.98377</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>225</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>2019-05-21</td>\n",
       "      <td>0.38</td>\n",
       "      <td>2</td>\n",
       "      <td>355</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3647</td>\n",
       "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
       "      <td>4632</td>\n",
       "      <td>Elisabeth</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Harlem</td>\n",
       "      <td>40.80902</td>\n",
       "      <td>-73.94190</td>\n",
       "      <td>Private room</td>\n",
       "      <td>150</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3831</td>\n",
       "      <td>Cozy Entire Floor of Brownstone</td>\n",
       "      <td>4869</td>\n",
       "      <td>LisaRoxanne</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Clinton Hill</td>\n",
       "      <td>40.68514</td>\n",
       "      <td>-73.95976</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>89</td>\n",
       "      <td>1</td>\n",
       "      <td>270</td>\n",
       "      <td>2019-07-05</td>\n",
       "      <td>4.64</td>\n",
       "      <td>1</td>\n",
       "      <td>194</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5022</td>\n",
       "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
       "      <td>7192</td>\n",
       "      <td>Laura</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>East Harlem</td>\n",
       "      <td>40.79851</td>\n",
       "      <td>-73.94399</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>80</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-11-19</td>\n",
       "      <td>0.10</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id                                              name  host_id  \\\n",
       "0  2539                Clean & quiet apt home by the park     2787   \n",
       "1  2595                             Skylit Midtown Castle     2845   \n",
       "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
       "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
       "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
       "\n",
       "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
       "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
       "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
       "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
       "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
       "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
       "\n",
       "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
       "0     Private room    149               1                  9  2018-10-19   \n",
       "1  Entire home/apt    225               1                 45  2019-05-21   \n",
       "2     Private room    150               3                  0         NaN   \n",
       "3  Entire home/apt     89               1                270  2019-07-05   \n",
       "4  Entire home/apt     80              10                  9  2018-11-19   \n",
       "\n",
       "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
       "0               0.21                               6               365  \n",
       "1               0.38                               2               355  \n",
       "2                NaN                               1               365  \n",
       "3               4.64                               1               194  \n",
       "4               0.10                               1                 0  "
      ]
     },
     "execution_count": 219,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"airbnb.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 3: Inspect the Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Inspect the data type for each column/categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 220,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                                  int64\n",
       "name                               object\n",
       "host_id                             int64\n",
       "host_name                          object\n",
       "neighbourhood_group                object\n",
       "neighbourhood                      object\n",
       "latitude                          float64\n",
       "longitude                         float64\n",
       "room_type                          object\n",
       "price                               int64\n",
       "minimum_nights                      int64\n",
       "number_of_reviews                   int64\n",
       "last_review                        object\n",
       "reviews_per_month                 float64\n",
       "calculated_host_listings_count      int64\n",
       "availability_365                    int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 220,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2. Change inappropriate data types "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                                         int64\n",
       "name                                      object\n",
       "host_id                                    int64\n",
       "host_name                                 object\n",
       "neighbourhood_group                       object\n",
       "neighbourhood                             object\n",
       "latitude                                 float64\n",
       "longitude                                float64\n",
       "room_type                                 object\n",
       "price                                      int64\n",
       "minimum_nights                             int64\n",
       "number_of_reviews                          int64\n",
       "last_review                       datetime64[ns]\n",
       "reviews_per_month                        float64\n",
       "calculated_host_listings_count             int64\n",
       "availability_365                           int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 221,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"last_review\"] = pd.to_datetime(df[\"last_review\"])\n",
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 222,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2539</td>\n",
       "      <td>Clean &amp; quiet apt home by the park</td>\n",
       "      <td>2787</td>\n",
       "      <td>John</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>40.64749</td>\n",
       "      <td>-73.97237</td>\n",
       "      <td>Private room</td>\n",
       "      <td>149</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-10-19</td>\n",
       "      <td>0.21</td>\n",
       "      <td>6</td>\n",
       "      <td>365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2595</td>\n",
       "      <td>Skylit Midtown Castle</td>\n",
       "      <td>2845</td>\n",
       "      <td>Jennifer</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Midtown</td>\n",
       "      <td>40.75362</td>\n",
       "      <td>-73.98377</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>225</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>2019-05-21</td>\n",
       "      <td>0.38</td>\n",
       "      <td>2</td>\n",
       "      <td>355</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3647</td>\n",
       "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
       "      <td>4632</td>\n",
       "      <td>Elisabeth</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Harlem</td>\n",
       "      <td>40.80902</td>\n",
       "      <td>-73.94190</td>\n",
       "      <td>Private room</td>\n",
       "      <td>150</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>NaT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3831</td>\n",
       "      <td>Cozy Entire Floor of Brownstone</td>\n",
       "      <td>4869</td>\n",
       "      <td>LisaRoxanne</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Clinton Hill</td>\n",
       "      <td>40.68514</td>\n",
       "      <td>-73.95976</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>89</td>\n",
       "      <td>1</td>\n",
       "      <td>270</td>\n",
       "      <td>2019-07-05</td>\n",
       "      <td>4.64</td>\n",
       "      <td>1</td>\n",
       "      <td>194</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5022</td>\n",
       "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
       "      <td>7192</td>\n",
       "      <td>Laura</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>East Harlem</td>\n",
       "      <td>40.79851</td>\n",
       "      <td>-73.94399</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>80</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-11-19</td>\n",
       "      <td>0.10</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id                                              name  host_id  \\\n",
       "0  2539                Clean & quiet apt home by the park     2787   \n",
       "1  2595                             Skylit Midtown Castle     2845   \n",
       "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
       "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
       "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
       "\n",
       "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
       "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
       "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
       "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
       "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
       "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
       "\n",
       "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
       "0     Private room    149               1                  9  2018-10-19   \n",
       "1  Entire home/apt    225               1                 45  2019-05-21   \n",
       "2     Private room    150               3                  0         NaT   \n",
       "3  Entire home/apt     89               1                270  2019-07-05   \n",
       "4  Entire home/apt     80              10                  9  2018-11-19   \n",
       "\n",
       "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
       "0               0.21                               6               365  \n",
       "1               0.38                               2               355  \n",
       "2                NaN                               1               365  \n",
       "3               4.64                               1               194  \n",
       "4               0.10                               1                 0  "
      ]
     },
     "execution_count": 222,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3. Check missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 223,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                                    0\n",
       "name                                 16\n",
       "host_id                               0\n",
       "host_name                            21\n",
       "neighbourhood_group                   0\n",
       "neighbourhood                         0\n",
       "latitude                              0\n",
       "longitude                             0\n",
       "room_type                             0\n",
       "price                                 0\n",
       "minimum_nights                        0\n",
       "number_of_reviews                     0\n",
       "last_review                       10052\n",
       "reviews_per_month                 10052\n",
       "calculated_host_listings_count        0\n",
       "availability_365                      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 223,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 4 : Show Amount of Data, Mean, Median, and other statistical prop."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 224,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>host_id</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4.889500e+04</td>\n",
       "      <td>4.889500e+04</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>38843.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.901714e+07</td>\n",
       "      <td>6.762001e+07</td>\n",
       "      <td>40.728949</td>\n",
       "      <td>-73.952170</td>\n",
       "      <td>152.720687</td>\n",
       "      <td>7.029962</td>\n",
       "      <td>23.274466</td>\n",
       "      <td>1.373221</td>\n",
       "      <td>7.143982</td>\n",
       "      <td>112.781327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.098311e+07</td>\n",
       "      <td>7.861097e+07</td>\n",
       "      <td>0.054530</td>\n",
       "      <td>0.046157</td>\n",
       "      <td>240.154170</td>\n",
       "      <td>20.510550</td>\n",
       "      <td>44.550582</td>\n",
       "      <td>1.680442</td>\n",
       "      <td>32.952519</td>\n",
       "      <td>131.622289</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.539000e+03</td>\n",
       "      <td>2.438000e+03</td>\n",
       "      <td>40.499790</td>\n",
       "      <td>-74.244420</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>9.471945e+06</td>\n",
       "      <td>7.822033e+06</td>\n",
       "      <td>40.690100</td>\n",
       "      <td>-73.983070</td>\n",
       "      <td>69.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.190000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.967728e+07</td>\n",
       "      <td>3.079382e+07</td>\n",
       "      <td>40.723070</td>\n",
       "      <td>-73.955680</td>\n",
       "      <td>106.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>45.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2.915218e+07</td>\n",
       "      <td>1.074344e+08</td>\n",
       "      <td>40.763115</td>\n",
       "      <td>-73.936275</td>\n",
       "      <td>175.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>2.020000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>227.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3.648724e+07</td>\n",
       "      <td>2.743213e+08</td>\n",
       "      <td>40.913060</td>\n",
       "      <td>-73.712990</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>1250.000000</td>\n",
       "      <td>629.000000</td>\n",
       "      <td>58.500000</td>\n",
       "      <td>327.000000</td>\n",
       "      <td>365.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 id       host_id      latitude     longitude         price  \\\n",
       "count  4.889500e+04  4.889500e+04  48895.000000  48895.000000  48895.000000   \n",
       "mean   1.901714e+07  6.762001e+07     40.728949    -73.952170    152.720687   \n",
       "std    1.098311e+07  7.861097e+07      0.054530      0.046157    240.154170   \n",
       "min    2.539000e+03  2.438000e+03     40.499790    -74.244420      0.000000   \n",
       "25%    9.471945e+06  7.822033e+06     40.690100    -73.983070     69.000000   \n",
       "50%    1.967728e+07  3.079382e+07     40.723070    -73.955680    106.000000   \n",
       "75%    2.915218e+07  1.074344e+08     40.763115    -73.936275    175.000000   \n",
       "max    3.648724e+07  2.743213e+08     40.913060    -73.712990  10000.000000   \n",
       "\n",
       "       minimum_nights  number_of_reviews  reviews_per_month  \\\n",
       "count    48895.000000       48895.000000       38843.000000   \n",
       "mean         7.029962          23.274466           1.373221   \n",
       "std         20.510550          44.550582           1.680442   \n",
       "min          1.000000           0.000000           0.010000   \n",
       "25%          1.000000           1.000000           0.190000   \n",
       "50%          3.000000           5.000000           0.720000   \n",
       "75%          5.000000          24.000000           2.020000   \n",
       "max       1250.000000         629.000000          58.500000   \n",
       "\n",
       "       calculated_host_listings_count  availability_365  \n",
       "count                    48895.000000      48895.000000  \n",
       "mean                         7.143982        112.781327  \n",
       "std                         32.952519        131.622289  \n",
       "min                          1.000000          0.000000  \n",
       "25%                          1.000000          0.000000  \n",
       "50%                          1.000000         45.000000  \n",
       "75%                          2.000000        227.000000  \n",
       "max                        327.000000        365.000000  "
      ]
     },
     "execution_count": 224,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 225,
   "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>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>38843.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "      <td>48895.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>152.720687</td>\n",
       "      <td>7.029962</td>\n",
       "      <td>23.274466</td>\n",
       "      <td>1.373221</td>\n",
       "      <td>7.143982</td>\n",
       "      <td>112.781327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>240.154170</td>\n",
       "      <td>20.510550</td>\n",
       "      <td>44.550582</td>\n",
       "      <td>1.680442</td>\n",
       "      <td>32.952519</td>\n",
       "      <td>131.622289</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>69.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.190000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>106.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>45.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>175.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>2.020000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>227.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10000.000000</td>\n",
       "      <td>1250.000000</td>\n",
       "      <td>629.000000</td>\n",
       "      <td>58.500000</td>\n",
       "      <td>327.000000</td>\n",
       "      <td>365.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              price  minimum_nights  number_of_reviews  reviews_per_month  \\\n",
       "count  48895.000000    48895.000000       48895.000000       38843.000000   \n",
       "mean     152.720687        7.029962          23.274466           1.373221   \n",
       "std      240.154170       20.510550          44.550582           1.680442   \n",
       "min        0.000000        1.000000           0.000000           0.010000   \n",
       "25%       69.000000        1.000000           1.000000           0.190000   \n",
       "50%      106.000000        3.000000           5.000000           0.720000   \n",
       "75%      175.000000        5.000000          24.000000           2.020000   \n",
       "max    10000.000000     1250.000000         629.000000          58.500000   \n",
       "\n",
       "       calculated_host_listings_count  availability_365  \n",
       "count                    48895.000000      48895.000000  \n",
       "mean                         7.143982        112.781327  \n",
       "std                         32.952519        131.622289  \n",
       "min                          1.000000          0.000000  \n",
       "25%                          1.000000          0.000000  \n",
       "50%                          1.000000         45.000000  \n",
       "75%                          2.000000        227.000000  \n",
       "max                        327.000000        365.000000  "
      ]
     },
     "execution_count": 225,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[:,[\"price\", \"minimum_nights\", \"number_of_reviews\", \n",
    "           \"reviews_per_month\", \"calculated_host_listings_count\", \"availability_365\"]].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 226,
   "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>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>48895.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>152.720687</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>240.154170</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>69.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>106.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>175.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10000.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              price\n",
       "count  48895.000000\n",
       "mean     152.720687\n",
       "std      240.154170\n",
       "min        0.000000\n",
       "25%       69.000000\n",
       "50%      106.000000\n",
       "75%      175.000000\n",
       "max    10000.000000"
      ]
     },
     "execution_count": 226,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[[\"price\"]].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 227,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "price    10000\n",
       "dtype: int64"
      ]
     },
     "execution_count": 227,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[[\"price\"]].max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 228,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "price    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 228,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[[\"price\"]].min()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 5: Get Rid of Missing Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 229,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                                    0\n",
       "name                                 16\n",
       "host_id                               0\n",
       "host_name                            21\n",
       "neighbourhood_group                   0\n",
       "neighbourhood                         0\n",
       "latitude                              0\n",
       "longitude                             0\n",
       "room_type                             0\n",
       "price                                 0\n",
       "minimum_nights                        0\n",
       "number_of_reviews                     0\n",
       "last_review                       10052\n",
       "reviews_per_month                 10052\n",
       "calculated_host_listings_count        0\n",
       "availability_365                      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 229,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 230,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(48895, 16)"
      ]
     },
     "execution_count": 230,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Drop rows of data with missing values at column 'name'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 231,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                                    0\n",
       "name                                  0\n",
       "host_id                               0\n",
       "host_name                             0\n",
       "neighbourhood_group                   0\n",
       "neighbourhood                         0\n",
       "latitude                              0\n",
       "longitude                             0\n",
       "room_type                             0\n",
       "price                                 0\n",
       "minimum_nights                        0\n",
       "number_of_reviews                     0\n",
       "last_review                       10037\n",
       "reviews_per_month                 10037\n",
       "calculated_host_listings_count        0\n",
       "availability_365                      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 231,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna(axis = 0, subset =['name', 'host_name'], inplace = True)\n",
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2539</td>\n",
       "      <td>Clean &amp; quiet apt home by the park</td>\n",
       "      <td>2787</td>\n",
       "      <td>John</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>40.64749</td>\n",
       "      <td>-73.97237</td>\n",
       "      <td>Private room</td>\n",
       "      <td>149</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-10-19</td>\n",
       "      <td>0.21</td>\n",
       "      <td>6</td>\n",
       "      <td>365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2595</td>\n",
       "      <td>Skylit Midtown Castle</td>\n",
       "      <td>2845</td>\n",
       "      <td>Jennifer</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Midtown</td>\n",
       "      <td>40.75362</td>\n",
       "      <td>-73.98377</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>225</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>2019-05-21</td>\n",
       "      <td>0.38</td>\n",
       "      <td>2</td>\n",
       "      <td>355</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3647</td>\n",
       "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
       "      <td>4632</td>\n",
       "      <td>Elisabeth</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Harlem</td>\n",
       "      <td>40.80902</td>\n",
       "      <td>-73.94190</td>\n",
       "      <td>Private room</td>\n",
       "      <td>150</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>NaT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3831</td>\n",
       "      <td>Cozy Entire Floor of Brownstone</td>\n",
       "      <td>4869</td>\n",
       "      <td>LisaRoxanne</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Clinton Hill</td>\n",
       "      <td>40.68514</td>\n",
       "      <td>-73.95976</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>89</td>\n",
       "      <td>1</td>\n",
       "      <td>270</td>\n",
       "      <td>2019-07-05</td>\n",
       "      <td>4.64</td>\n",
       "      <td>1</td>\n",
       "      <td>194</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5022</td>\n",
       "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
       "      <td>7192</td>\n",
       "      <td>Laura</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>East Harlem</td>\n",
       "      <td>40.79851</td>\n",
       "      <td>-73.94399</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>80</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-11-19</td>\n",
       "      <td>0.10</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id                                              name  host_id  \\\n",
       "0  2539                Clean & quiet apt home by the park     2787   \n",
       "1  2595                             Skylit Midtown Castle     2845   \n",
       "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
       "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
       "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
       "\n",
       "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
       "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
       "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
       "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
       "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
       "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
       "\n",
       "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
       "0     Private room    149               1                  9  2018-10-19   \n",
       "1  Entire home/apt    225               1                 45  2019-05-21   \n",
       "2     Private room    150               3                  0         NaT   \n",
       "3  Entire home/apt     89               1                270  2019-07-05   \n",
       "4  Entire home/apt     80              10                  9  2018-11-19   \n",
       "\n",
       "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
       "0               0.21                               6               365  \n",
       "1               0.38                               2               355  \n",
       "2                NaN                               1               365  \n",
       "3               4.64                               1               194  \n",
       "4               0.10                               1                 0  "
      ]
     },
     "execution_count": 232,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 233,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(48858, 16)"
      ]
     },
     "execution_count": 233,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2. Replace missing data at column 'review_per_month' by its mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 234,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                                    0\n",
       "name                                  0\n",
       "host_id                               0\n",
       "host_name                             0\n",
       "neighbourhood_group                   0\n",
       "neighbourhood                         0\n",
       "latitude                              0\n",
       "longitude                             0\n",
       "room_type                             0\n",
       "price                                 0\n",
       "minimum_nights                        0\n",
       "number_of_reviews                     0\n",
       "last_review                       10037\n",
       "reviews_per_month                     0\n",
       "calculated_host_listings_count        0\n",
       "availability_365                      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 234,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['reviews_per_month'] = df['reviews_per_month'].fillna(df['reviews_per_month'].mean())\n",
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 235,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(48858, 16)"
      ]
     },
     "execution_count": 235,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3. Replace missing data at column 'last_review' with most common date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 236,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                                0\n",
       "name                              0\n",
       "host_id                           0\n",
       "host_name                         0\n",
       "neighbourhood_group               0\n",
       "neighbourhood                     0\n",
       "latitude                          0\n",
       "longitude                         0\n",
       "room_type                         0\n",
       "price                             0\n",
       "minimum_nights                    0\n",
       "number_of_reviews                 0\n",
       "last_review                       0\n",
       "reviews_per_month                 0\n",
       "calculated_host_listings_count    0\n",
       "availability_365                  0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 236,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['last_review'] = df['last_review'].fillna(df['last_review'].mode()[0])\n",
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 237,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(48858, 16)"
      ]
     },
     "execution_count": 237,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 6: Make a new category based on price"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 238,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    48858.000000\n",
       "mean       152.740309\n",
       "std        240.232386\n",
       "min          0.000000\n",
       "25%         69.000000\n",
       "50%        106.000000\n",
       "75%        175.000000\n",
       "max      10000.000000\n",
       "Name: price, dtype: float64"
      ]
     },
     "execution_count": 238,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['price'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 242,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "      <th>expensiveness</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2539</td>\n",
       "      <td>Clean &amp; quiet apt home by the park</td>\n",
       "      <td>2787</td>\n",
       "      <td>John</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>40.64749</td>\n",
       "      <td>-73.97237</td>\n",
       "      <td>Private room</td>\n",
       "      <td>149</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-10-19</td>\n",
       "      <td>0.210000</td>\n",
       "      <td>6</td>\n",
       "      <td>365</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2595</td>\n",
       "      <td>Skylit Midtown Castle</td>\n",
       "      <td>2845</td>\n",
       "      <td>Jennifer</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Midtown</td>\n",
       "      <td>40.75362</td>\n",
       "      <td>-73.98377</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>225</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>2019-05-21</td>\n",
       "      <td>0.380000</td>\n",
       "      <td>2</td>\n",
       "      <td>355</td>\n",
       "      <td>Expensive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3647</td>\n",
       "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
       "      <td>4632</td>\n",
       "      <td>Elisabeth</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Harlem</td>\n",
       "      <td>40.80902</td>\n",
       "      <td>-73.94190</td>\n",
       "      <td>Private room</td>\n",
       "      <td>150</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2019-06-23</td>\n",
       "      <td>1.373229</td>\n",
       "      <td>1</td>\n",
       "      <td>365</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3831</td>\n",
       "      <td>Cozy Entire Floor of Brownstone</td>\n",
       "      <td>4869</td>\n",
       "      <td>LisaRoxanne</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Clinton Hill</td>\n",
       "      <td>40.68514</td>\n",
       "      <td>-73.95976</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>89</td>\n",
       "      <td>1</td>\n",
       "      <td>270</td>\n",
       "      <td>2019-07-05</td>\n",
       "      <td>4.640000</td>\n",
       "      <td>1</td>\n",
       "      <td>194</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5022</td>\n",
       "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
       "      <td>7192</td>\n",
       "      <td>Laura</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>East Harlem</td>\n",
       "      <td>40.79851</td>\n",
       "      <td>-73.94399</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>80</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-11-19</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id                                              name  host_id  \\\n",
       "0  2539                Clean & quiet apt home by the park     2787   \n",
       "1  2595                             Skylit Midtown Castle     2845   \n",
       "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
       "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
       "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
       "\n",
       "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
       "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
       "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
       "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
       "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
       "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
       "\n",
       "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
       "0     Private room    149               1                  9  2018-10-19   \n",
       "1  Entire home/apt    225               1                 45  2019-05-21   \n",
       "2     Private room    150               3                  0  2019-06-23   \n",
       "3  Entire home/apt     89               1                270  2019-07-05   \n",
       "4  Entire home/apt     80              10                  9  2018-11-19   \n",
       "\n",
       "   reviews_per_month  calculated_host_listings_count  availability_365  \\\n",
       "0           0.210000                               6               365   \n",
       "1           0.380000                               2               355   \n",
       "2           1.373229                               1               365   \n",
       "3           4.640000                               1               194   \n",
       "4           0.100000                               1                 0   \n",
       "\n",
       "  expensiveness  \n",
       "0        Medium  \n",
       "1     Expensive  \n",
       "2        Medium  \n",
       "3         Cheap  \n",
       "4         Cheap  "
      ]
     },
     "execution_count": 242,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[['expensiveness']] = np.where(df[\"price\"]>175, \"Expensive\", np.where(df['price']>106, 'Medium', 'Cheap'))\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 7: Filter All Data with 'last_review' above 2019"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 248,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "      <th>expensiveness</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2595</td>\n",
       "      <td>Skylit Midtown Castle</td>\n",
       "      <td>2845</td>\n",
       "      <td>Jennifer</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Midtown</td>\n",
       "      <td>40.75362</td>\n",
       "      <td>-73.98377</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>225</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>2019-05-21</td>\n",
       "      <td>0.380000</td>\n",
       "      <td>2</td>\n",
       "      <td>355</td>\n",
       "      <td>Expensive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3647</td>\n",
       "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
       "      <td>4632</td>\n",
       "      <td>Elisabeth</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Harlem</td>\n",
       "      <td>40.80902</td>\n",
       "      <td>-73.94190</td>\n",
       "      <td>Private room</td>\n",
       "      <td>150</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2019-06-23</td>\n",
       "      <td>1.373229</td>\n",
       "      <td>1</td>\n",
       "      <td>365</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3831</td>\n",
       "      <td>Cozy Entire Floor of Brownstone</td>\n",
       "      <td>4869</td>\n",
       "      <td>LisaRoxanne</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Clinton Hill</td>\n",
       "      <td>40.68514</td>\n",
       "      <td>-73.95976</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>89</td>\n",
       "      <td>1</td>\n",
       "      <td>270</td>\n",
       "      <td>2019-07-05</td>\n",
       "      <td>4.640000</td>\n",
       "      <td>1</td>\n",
       "      <td>194</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5099</td>\n",
       "      <td>Large Cozy 1 BR Apartment In Midtown East</td>\n",
       "      <td>7322</td>\n",
       "      <td>Chris</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Murray Hill</td>\n",
       "      <td>40.74767</td>\n",
       "      <td>-73.97500</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>200</td>\n",
       "      <td>3</td>\n",
       "      <td>74</td>\n",
       "      <td>2019-06-22</td>\n",
       "      <td>0.590000</td>\n",
       "      <td>1</td>\n",
       "      <td>129</td>\n",
       "      <td>Expensive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5178</td>\n",
       "      <td>Large Furnished Room Near B'way</td>\n",
       "      <td>8967</td>\n",
       "      <td>Shunichi</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Hell's Kitchen</td>\n",
       "      <td>40.76489</td>\n",
       "      <td>-73.98493</td>\n",
       "      <td>Private room</td>\n",
       "      <td>79</td>\n",
       "      <td>2</td>\n",
       "      <td>430</td>\n",
       "      <td>2019-06-24</td>\n",
       "      <td>3.470000</td>\n",
       "      <td>1</td>\n",
       "      <td>220</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id                                       name  host_id    host_name  \\\n",
       "1  2595                      Skylit Midtown Castle     2845     Jennifer   \n",
       "2  3647        THE VILLAGE OF HARLEM....NEW YORK !     4632    Elisabeth   \n",
       "3  3831            Cozy Entire Floor of Brownstone     4869  LisaRoxanne   \n",
       "5  5099  Large Cozy 1 BR Apartment In Midtown East     7322        Chris   \n",
       "7  5178           Large Furnished Room Near B'way      8967     Shunichi   \n",
       "\n",
       "  neighbourhood_group   neighbourhood  latitude  longitude        room_type  \\\n",
       "1           Manhattan         Midtown  40.75362  -73.98377  Entire home/apt   \n",
       "2           Manhattan          Harlem  40.80902  -73.94190     Private room   \n",
       "3            Brooklyn    Clinton Hill  40.68514  -73.95976  Entire home/apt   \n",
       "5           Manhattan     Murray Hill  40.74767  -73.97500  Entire home/apt   \n",
       "7           Manhattan  Hell's Kitchen  40.76489  -73.98493     Private room   \n",
       "\n",
       "   price  minimum_nights  number_of_reviews last_review  reviews_per_month  \\\n",
       "1    225               1                 45  2019-05-21           0.380000   \n",
       "2    150               3                  0  2019-06-23           1.373229   \n",
       "3     89               1                270  2019-07-05           4.640000   \n",
       "5    200               3                 74  2019-06-22           0.590000   \n",
       "7     79               2                430  2019-06-24           3.470000   \n",
       "\n",
       "   calculated_host_listings_count  availability_365 expensiveness  \n",
       "1                               2               355     Expensive  \n",
       "2                               1               365        Medium  \n",
       "3                               1               194         Cheap  \n",
       "5                               1               129     Expensive  \n",
       "7                               1               220         Cheap  "
      ]
     },
     "execution_count": 248,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_2019 = df.loc[df['last_review']>'2019-01-01']\n",
    "df_2019.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(34842, 17)"
      ]
     },
     "execution_count": 249,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_2019.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 8: Visualize the price to compare price of available room"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 251,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Hillside Hotel                                       18\n",
       "Home away from home                                  17\n",
       "New york Multi-unit building                         16\n",
       "Brooklyn Apartment                                   12\n",
       "Loft Suite @ The Box House Hotel                     11\n",
       "                                                     ..\n",
       "2BED 2 BATH/COLUMBUS CIRCLE/ BALCONY                  1\n",
       "Charming Housebarge w/ outside deck                   1\n",
       "Beach House Retreat. 15 minutes from Manhattan.       1\n",
       "Beautiful Meatpacking District Loft                   1\n",
       "420 friendly Beautiful rm with plenty of sunlight     1\n",
       "Name: name, Length: 47884, dtype: int64"
      ]
     },
     "execution_count": 251,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['name'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 252,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Entire home/apt    25393\n",
       "Private room       22306\n",
       "Shared room         1159\n",
       "Name: room_type, dtype: int64"
      ]
     },
     "execution_count": 252,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['room_type'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 260,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "      <th>expensiveness</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2595</td>\n",
       "      <td>Skylit Midtown Castle</td>\n",
       "      <td>2845</td>\n",
       "      <td>Jennifer</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Midtown</td>\n",
       "      <td>40.75362</td>\n",
       "      <td>-73.98377</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>225</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>2019-05-21</td>\n",
       "      <td>0.38</td>\n",
       "      <td>2</td>\n",
       "      <td>355</td>\n",
       "      <td>Expensive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3831</td>\n",
       "      <td>Cozy Entire Floor of Brownstone</td>\n",
       "      <td>4869</td>\n",
       "      <td>LisaRoxanne</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Clinton Hill</td>\n",
       "      <td>40.68514</td>\n",
       "      <td>-73.95976</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>89</td>\n",
       "      <td>1</td>\n",
       "      <td>270</td>\n",
       "      <td>2019-07-05</td>\n",
       "      <td>4.64</td>\n",
       "      <td>1</td>\n",
       "      <td>194</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5022</td>\n",
       "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
       "      <td>7192</td>\n",
       "      <td>Laura</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>East Harlem</td>\n",
       "      <td>40.79851</td>\n",
       "      <td>-73.94399</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>80</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-11-19</td>\n",
       "      <td>0.10</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5099</td>\n",
       "      <td>Large Cozy 1 BR Apartment In Midtown East</td>\n",
       "      <td>7322</td>\n",
       "      <td>Chris</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Murray Hill</td>\n",
       "      <td>40.74767</td>\n",
       "      <td>-73.97500</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>200</td>\n",
       "      <td>3</td>\n",
       "      <td>74</td>\n",
       "      <td>2019-06-22</td>\n",
       "      <td>0.59</td>\n",
       "      <td>1</td>\n",
       "      <td>129</td>\n",
       "      <td>Expensive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>5238</td>\n",
       "      <td>Cute &amp; Cozy Lower East Side 1 bdrm</td>\n",
       "      <td>7549</td>\n",
       "      <td>Ben</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Chinatown</td>\n",
       "      <td>40.71344</td>\n",
       "      <td>-73.99037</td>\n",
       "      <td>Entire home/apt</td>\n",
       "      <td>150</td>\n",
       "      <td>1</td>\n",
       "      <td>160</td>\n",
       "      <td>2019-06-09</td>\n",
       "      <td>1.33</td>\n",
       "      <td>4</td>\n",
       "      <td>188</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id                                              name  host_id  \\\n",
       "1  2595                             Skylit Midtown Castle     2845   \n",
       "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
       "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
       "5  5099         Large Cozy 1 BR Apartment In Midtown East     7322   \n",
       "9  5238                Cute & Cozy Lower East Side 1 bdrm     7549   \n",
       "\n",
       "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
       "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
       "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
       "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
       "5        Chris           Manhattan   Murray Hill  40.74767  -73.97500   \n",
       "9          Ben           Manhattan     Chinatown  40.71344  -73.99037   \n",
       "\n",
       "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
       "1  Entire home/apt    225               1                 45  2019-05-21   \n",
       "3  Entire home/apt     89               1                270  2019-07-05   \n",
       "4  Entire home/apt     80              10                  9  2018-11-19   \n",
       "5  Entire home/apt    200               3                 74  2019-06-22   \n",
       "9  Entire home/apt    150               1                160  2019-06-09   \n",
       "\n",
       "   reviews_per_month  calculated_host_listings_count  availability_365  \\\n",
       "1               0.38                               2               355   \n",
       "3               4.64                               1               194   \n",
       "4               0.10                               1                 0   \n",
       "5               0.59                               1               129   \n",
       "9               1.33                               4               188   \n",
       "\n",
       "  expensiveness  \n",
       "1     Expensive  \n",
       "3         Cheap  \n",
       "4         Cheap  \n",
       "5     Expensive  \n",
       "9        Medium  "
      ]
     },
     "execution_count": 260,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_home_apt= df.loc[df['room_type'] == 'Entire home/apt']\n",
    "df_home_apt.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 263,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "211.80699405347931"
      ]
     },
     "execution_count": 263,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_home_apt['price'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 261,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "      <th>expensiveness</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2539</td>\n",
       "      <td>Clean &amp; quiet apt home by the park</td>\n",
       "      <td>2787</td>\n",
       "      <td>John</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Kensington</td>\n",
       "      <td>40.64749</td>\n",
       "      <td>-73.97237</td>\n",
       "      <td>Private room</td>\n",
       "      <td>149</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>2018-10-19</td>\n",
       "      <td>0.210000</td>\n",
       "      <td>6</td>\n",
       "      <td>365</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3647</td>\n",
       "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
       "      <td>4632</td>\n",
       "      <td>Elisabeth</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Harlem</td>\n",
       "      <td>40.80902</td>\n",
       "      <td>-73.94190</td>\n",
       "      <td>Private room</td>\n",
       "      <td>150</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2019-06-23</td>\n",
       "      <td>1.373229</td>\n",
       "      <td>1</td>\n",
       "      <td>365</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5121</td>\n",
       "      <td>BlissArtsSpace!</td>\n",
       "      <td>7356</td>\n",
       "      <td>Garon</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>Bedford-Stuyvesant</td>\n",
       "      <td>40.68688</td>\n",
       "      <td>-73.95596</td>\n",
       "      <td>Private room</td>\n",
       "      <td>60</td>\n",
       "      <td>45</td>\n",
       "      <td>49</td>\n",
       "      <td>2017-10-05</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5178</td>\n",
       "      <td>Large Furnished Room Near B'way</td>\n",
       "      <td>8967</td>\n",
       "      <td>Shunichi</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Hell's Kitchen</td>\n",
       "      <td>40.76489</td>\n",
       "      <td>-73.98493</td>\n",
       "      <td>Private room</td>\n",
       "      <td>79</td>\n",
       "      <td>2</td>\n",
       "      <td>430</td>\n",
       "      <td>2019-06-24</td>\n",
       "      <td>3.470000</td>\n",
       "      <td>1</td>\n",
       "      <td>220</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>5203</td>\n",
       "      <td>Cozy Clean Guest Room - Family Apt</td>\n",
       "      <td>7490</td>\n",
       "      <td>MaryEllen</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Upper West Side</td>\n",
       "      <td>40.80178</td>\n",
       "      <td>-73.96723</td>\n",
       "      <td>Private room</td>\n",
       "      <td>79</td>\n",
       "      <td>2</td>\n",
       "      <td>118</td>\n",
       "      <td>2017-07-21</td>\n",
       "      <td>0.990000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id                                 name  host_id  host_name  \\\n",
       "0  2539   Clean & quiet apt home by the park     2787       John   \n",
       "2  3647  THE VILLAGE OF HARLEM....NEW YORK !     4632  Elisabeth   \n",
       "6  5121                      BlissArtsSpace!     7356      Garon   \n",
       "7  5178     Large Furnished Room Near B'way      8967   Shunichi   \n",
       "8  5203   Cozy Clean Guest Room - Family Apt     7490  MaryEllen   \n",
       "\n",
       "  neighbourhood_group       neighbourhood  latitude  longitude     room_type  \\\n",
       "0            Brooklyn          Kensington  40.64749  -73.97237  Private room   \n",
       "2           Manhattan              Harlem  40.80902  -73.94190  Private room   \n",
       "6            Brooklyn  Bedford-Stuyvesant  40.68688  -73.95596  Private room   \n",
       "7           Manhattan      Hell's Kitchen  40.76489  -73.98493  Private room   \n",
       "8           Manhattan     Upper West Side  40.80178  -73.96723  Private room   \n",
       "\n",
       "   price  minimum_nights  number_of_reviews last_review  reviews_per_month  \\\n",
       "0    149               1                  9  2018-10-19           0.210000   \n",
       "2    150               3                  0  2019-06-23           1.373229   \n",
       "6     60              45                 49  2017-10-05           0.400000   \n",
       "7     79               2                430  2019-06-24           3.470000   \n",
       "8     79               2                118  2017-07-21           0.990000   \n",
       "\n",
       "   calculated_host_listings_count  availability_365 expensiveness  \n",
       "0                               6               365        Medium  \n",
       "2                               1               365        Medium  \n",
       "6                               1                 0         Cheap  \n",
       "7                               1               220         Cheap  \n",
       "8                               1                 0         Cheap  "
      ]
     },
     "execution_count": 261,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_private_room= df.loc[df['room_type'] == 'Private room']\n",
    "df_private_room.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 266,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "89.79436026181297"
      ]
     },
     "execution_count": 266,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_private_room['price'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 262,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>name</th>\n",
       "      <th>host_id</th>\n",
       "      <th>host_name</th>\n",
       "      <th>neighbourhood_group</th>\n",
       "      <th>neighbourhood</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>room_type</th>\n",
       "      <th>price</th>\n",
       "      <th>minimum_nights</th>\n",
       "      <th>number_of_reviews</th>\n",
       "      <th>last_review</th>\n",
       "      <th>reviews_per_month</th>\n",
       "      <th>calculated_host_listings_count</th>\n",
       "      <th>availability_365</th>\n",
       "      <th>expensiveness</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>12048</td>\n",
       "      <td>LowerEastSide apt share shortterm 1</td>\n",
       "      <td>7549</td>\n",
       "      <td>Ben</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Lower East Side</td>\n",
       "      <td>40.71401</td>\n",
       "      <td>-73.98917</td>\n",
       "      <td>Shared room</td>\n",
       "      <td>40</td>\n",
       "      <td>1</td>\n",
       "      <td>214</td>\n",
       "      <td>2019-07-05</td>\n",
       "      <td>1.810000</td>\n",
       "      <td>4</td>\n",
       "      <td>188</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>203</th>\n",
       "      <td>54453</td>\n",
       "      <td>MIDTOWN WEST - Large alcove studio</td>\n",
       "      <td>255583</td>\n",
       "      <td>Anka</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Hell's Kitchen</td>\n",
       "      <td>40.76548</td>\n",
       "      <td>-73.98474</td>\n",
       "      <td>Shared room</td>\n",
       "      <td>105</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>2014-01-07</td>\n",
       "      <td>0.090000</td>\n",
       "      <td>1</td>\n",
       "      <td>363</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>357</th>\n",
       "      <td>99070</td>\n",
       "      <td>Comfortable Cozy Space in El Barrio</td>\n",
       "      <td>522065</td>\n",
       "      <td>Liz And Melissa</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>East Harlem</td>\n",
       "      <td>40.79406</td>\n",
       "      <td>-73.94102</td>\n",
       "      <td>Shared room</td>\n",
       "      <td>65</td>\n",
       "      <td>7</td>\n",
       "      <td>131</td>\n",
       "      <td>2019-05-26</td>\n",
       "      <td>1.310000</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>492</th>\n",
       "      <td>173072</td>\n",
       "      <td>Cozy Pre-War Harlem Apartment</td>\n",
       "      <td>826192</td>\n",
       "      <td>Lewis</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Harlem</td>\n",
       "      <td>40.80827</td>\n",
       "      <td>-73.95329</td>\n",
       "      <td>Shared room</td>\n",
       "      <td>49</td>\n",
       "      <td>3</td>\n",
       "      <td>168</td>\n",
       "      <td>2019-07-06</td>\n",
       "      <td>4.600000</td>\n",
       "      <td>1</td>\n",
       "      <td>248</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>545</th>\n",
       "      <td>200645</td>\n",
       "      <td>Best Manhattan Studio Deal!</td>\n",
       "      <td>933378</td>\n",
       "      <td>Edo</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>Upper East Side</td>\n",
       "      <td>40.76739</td>\n",
       "      <td>-73.95570</td>\n",
       "      <td>Shared room</td>\n",
       "      <td>90</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2019-06-23</td>\n",
       "      <td>1.373229</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Cheap</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         id                                 name  host_id        host_name  \\\n",
       "39    12048  LowerEastSide apt share shortterm 1     7549              Ben   \n",
       "203   54453   MIDTOWN WEST - Large alcove studio   255583             Anka   \n",
       "357   99070  Comfortable Cozy Space in El Barrio   522065  Liz And Melissa   \n",
       "492  173072        Cozy Pre-War Harlem Apartment   826192            Lewis   \n",
       "545  200645       Best Manhattan Studio Deal!      933378              Edo   \n",
       "\n",
       "    neighbourhood_group    neighbourhood  latitude  longitude    room_type  \\\n",
       "39            Manhattan  Lower East Side  40.71401  -73.98917  Shared room   \n",
       "203           Manhattan   Hell's Kitchen  40.76548  -73.98474  Shared room   \n",
       "357           Manhattan      East Harlem  40.79406  -73.94102  Shared room   \n",
       "492           Manhattan           Harlem  40.80827  -73.95329  Shared room   \n",
       "545           Manhattan  Upper East Side  40.76739  -73.95570  Shared room   \n",
       "\n",
       "     price  minimum_nights  number_of_reviews last_review  reviews_per_month  \\\n",
       "39      40               1                214  2019-07-05           1.810000   \n",
       "203    105               6                 10  2014-01-07           0.090000   \n",
       "357     65               7                131  2019-05-26           1.310000   \n",
       "492     49               3                168  2019-07-06           4.600000   \n",
       "545     90               1                  0  2019-06-23           1.373229   \n",
       "\n",
       "     calculated_host_listings_count  availability_365 expensiveness  \n",
       "39                                4               188         Cheap  \n",
       "203                               1               363         Cheap  \n",
       "357                               2                 0         Cheap  \n",
       "492                               1               248         Cheap  \n",
       "545                               1                 0         Cheap  "
      ]
     },
     "execution_count": 262,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_shared_room= df.loc[df['room_type'] == 'Shared room']\n",
    "df_shared_room.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 271,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "70.07592752372734"
      ]
     },
     "execution_count": 271,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_shared_room['price'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 272,
   "metadata": {},
   "outputs": [],
   "source": [
    "room_type = ['Entire Home/Apt', 'Private Room', 'Shared Room']\n",
    "average_price = [df_home_apt['price'].mean(), df_private_room['price'].mean(), df_shared_room['price'].mean()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 273,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<function matplotlib.pyplot.show(close=None, block=None)>"
      ]
     },
     "execution_count": 273,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAagAAAEYCAYAAAAJeGK1AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAk4klEQVR4nO3deZwcVb338c+XENnCngEDBAYwgIAYdAAVAgjIJrKvIoblCnhBFvVRVLzkcXtwQbwuiAEjQUnYUfSlAhdJQL2AEwxhCVGWYEJCGPYQIJjwe/44p0ll6JnpmUxP18x8369Xv7rq1Pbrru7+VZ06fUoRgZmZWdms1OgAzMzMqnGCMjOzUnKCMjOzUnKCMjOzUnKCMjOzUnKCMjOzUnKCMrOqJD0kac9Gx1EWksZImtXoOAYTJ6h+TNJsSa9JekXS05KukDSsgfFsmmOpPELSosL4mEbF1hOS1shx/77RsfQGSVMkvZ5f07OSbpQ0oqP5I2K7iJhShzj2k3SnpIWS2iRNlXRwb2+nt0XEXRGxdaPjGEycoPq/j0XEMGA0sCPwpUYFEhH/iohhlUcufm+h7K5GxdZDRwKLgX07+yHvKUkr9/Y6a3Bm3jdbAesAF7efoZ5xSToSuA64EtgE2BD4L+Bj9dpmb2jQvhr0nKAGiIh4GriFlKgAkHRwrqZ5MR89v7sw7d257MU8z8GFaVdIukTSH/LR9l8kvVPSDyS9IOkRSTvWGlte9lVJ6xfK3p+PnodKOjFv40eSXsrr37sw79qSfi5pvqSnJH1D0pAq29kon1GuVyjbMZ8tDJX0rny0/lIuu6aL0McClwIzgOPz+j6Qz1bf2r6kwyTNyMMrSTpP0mOSnpN0bSUeSc35rPIUSf8C/pTLr8vrfCmfWWxXWPf6kn4r6WVJf8uv/c+F6dtIuk3S85JmSTq6ln0SEc8DNwDb5/XMlvTF/DoWSVo5l+2Tpw+R9OX8uhZKmiZpZHdikCTg+8DXI+LyiHgpIt6MiKkR8anC+3e+pCclPSPpSklrt3v/TpI0J38WT5e0k6QZ+bP848L2uvpcnSRpZn49j0s6rTBtT0lz83vyNPCLSllhni/mz+PC/Lr3zuWrKH1X5uXHDySt0m69n8uvb76kk2rZZ4NSRPjRTx/AbGCfPLwJ8ADw33l8K2AR8BFgKPAF4FHgHXn8UeDLeXwvYCGwdV72CuBZ4P3AqqQf0ieATwJDgG8Ad9QQXwDvysO/Bz5dmHYx8KM8fCKwBDg3x3YM8BKwXp7+a+BnwBrABsC9wGkdbPNPwKcK498FLs3Dk4GvkA7MVgV26yT2TYE3gW2BzwEzCtMeAz5SGL8OOC8PnwPcnffHKjnuyXlac35PrsyvZbVcfjKwZp7/B8D0wrqvzo/VcyxzgD/naWvk8ZOAlYH35f22XQevaQrwH3l4eH6vfln4LE0HRhbims2yz9f/IX2+tgYEvBdYvzsxANvk1795J+/7yaTP5hbAMODGQoyV9+/SvP/2BV7Pn48NgI2BZ4A9avxcfRTYMr+ePYBXgfflaXvmZb+d98tquWxunr51ft0bFWLbMg9/LX8GNgCagL+SknJxvV/LMR2Yt7tuo39PyvhoeAB+rMDOSz8gr5CSSwC3A+vkaV8Fri3MuxLwVP6CjAGeBlYqTJ8MjMvDVwCXFaZ9BphZGH8P8GIN8RUT1DHAX/LwkLz9nfP4icA8QIVl7wVOIFUBLSb/aOZpx9FBggT+A/hTHlb+Edk9j18JjAc2qSH288mJAtgIWArsmMe/AUzIw2uSDgQ2y+Mzgb0L6xkB/Jv0492c35MtOtnuOnmetfP79G/ygUNh25UEdQxwV7vlfwZc0MG6p+QfwxfzZ+EqoKnwWTq5yuerkqBmAYdUWWfNMQC75te2aiev/3bgPwvjW1d5/zYuTH8OOKYwfgNwTlefqw62/Wvg7Dy8J/BGMVaWT1DvIiXDfYCh7dbzGHBgYXw/YHZhHa8BKxemPwN8oDvf/cHycBVf/3doRKxJ+uBvQzoyhvSj+mRlpoh4k/RjvXGeNieXVTyZp1UsKAy/VmW8u40xfgNsK2kL0lndSxFxb2H6U5G/rYV4NgI2Ix1pzs9VOC+SfgA36GA71wMflLQRsDvpB61y7esLpKR1r1K15smdxPtJ0g84ETEPmEqq8gOYBByeq20OB+6LiMp7vRlwUyHWmaTktmFh3XMqA7nq7MJcdfYyKSlA2o9NpB/mOdWWzdvapbKtvL3jgXd28rrOioh1ImLjiDg+Ito6WHd7I0k/vO11J4bn8nNn1/OW+9zm4ZVZ/v3rzmezo88Vkg6QdHeumnyRdDYzvDBvW0S8Xi3IiHiUdLY8DnhG0tX5M9fRa9ioMP5cRCwpjL9K979Pg4IT1AAREVNJZz7fy0XzSD8ewFv1/yNJR87zgJGSivt/0zytXvG9DlxL+vE6Afhlu1k2zjEW45lH+tFcDAzPP6zrRMRaEbEdVUTEi8CtwNHAx0nVa5GnPR0Rn4qIjYDTgEskvav9OiR9CBgFfClfG3oa2AU4TtLKEfEw6UfngLyNSYXF5wAHFGJdJyJWjYjie1v8wfw4cAjpSHxt0lkCpETaRqoO2qQw/8h225rablvDIuLT1d6bGnR2a4M5pOqwauW1xjArz39EJ9tZ7nNL+hwsYfkk1B1VP1f54OIG0vdlw4hYh1QNXZy301s9RMSkiNgtxxuk6sCOXsO8HsY/qDlBDSw/AD4iaTQpGXxU0t6ShpKuoywm1YffQ6qW+oJS44E9Sa2orq5zfFeSql0OBn7VbtoGwFk5nqOAdwO/j4j5pIRzkaS18kX0LSXt0cl2JpHOgI6gkDwkHSWp8mP/AulHZWmV5ccCt5Gu+YzOj+1J14EOKGzjLNJZ2nWFZS8Fvilps7zNJkmHdBLrmqT98lxe/7cqEyJiKekazDhJq0vaJr+uit8BW0k6Ib9vQ3ODgXfT+y4Hvi5plJIdlBq91BxDPlD4LPDV3EChsj93kzQ+zzYZOFfS5kp/mfgWcE27M47uqPq5Il17XYV8ECDpANI1rZpI2lrSXjnRvU46c6t8liYD5+d9P5zUSrH9591q4AQ1gOTqmiuBr0bELOATwI9IF60/RmqS/kZEvEFKEgfkaZcAn4yIR+oc319IDQ/ui4jZ7SbfQzpreRb4JnBkRFSqhD5J+kF5mJRYrqfzaqKb87oWRMT9hfKdgHskvZLnOTsiniguKGlV0tnXj/IZV+XxBOmsr1LNN5lUrfqniHi2sIr/zuu+VdJC0sXyXTqJ9UrS2dhT+fXd3W76maQzq6fz9ieTEhoRsZD0o3os6Qj9aZZd1O9t3ycd9NwKvAz8nHRdsFsxRMT1pOtWJ+f5F5Cuq/0mzzKB9DrvJDXMeZ10DbSnqn6uctxn5df0AulM9uZurHcV4MK83qdJifDLedo3gFZS688HgPtymXWTlq+eNasvSX8CJkXE5YWyE0mty3ZrWGD9hKRvA++MiLFdzjzI+XPV//kMyvqMpJ1IzZC7+v+RZUr/MdohV6vtDJwC3NTouMz6gv8dbX1C0kTgUFK12sIGh9OfrEmq1tuI1Bz5IpZVh5kNaK7iMzOzUnIVn5mZlVK/ruIbPnx4NDc3NzoMMzNbAdOmTXs2Ipral/frBNXc3Exra2ujwzAzsxUg6clq5a7iMzOzUnKCMjOzUnKCMjOzUnKCMjOzUnKCMjOzUnKCMjOzUnKCMjOzUnKCMjOzUnKCMjOzUurXPUn0huVuBm19zn0Vm1lHfAZlZmal5ARlZmal5ARlZmal5ARlZmal5ARlZmal5ARlZmal5ARlZmalVLcEJWmkpDskzZT0kKSzc/l6km6T9M/8vG5hmS9JelTSLEn71Ss2MzMrv3qeQS0BPhcR7wY+AJwhaVvgPOD2iBgF3J7HydOOBbYD9gcukTSkjvGZmVmJ1S1BRcT8iLgvDy8EZgIbA4cAE/NsE4FD8/AhwNURsTgingAeBXauV3xmZlZufXINSlIzsCNwD7BhRMyHlMSADfJsGwNzCovNzWXt13WqpFZJrW1tbXWN28zMGqfuCUrSMOAG4JyIeLmzWauUva2ntogYHxEtEdHS1NTUW2GamVnJ1DVBSRpKSk5XRcSNuXiBpBF5+gjgmVw+FxhZWHwTYF494zMzs/KqZys+AT8HZkbE9wuTbgbG5uGxwG8K5cdKWkXS5sAo4N56xWdmZuVWz9tt7AqcADwgaXou+zJwIXCtpFOAfwFHAUTEQ5KuBR4mtQA8IyKW1jE+MzMrsbolqIj4M9WvKwHs3cEy3wS+Wa+YzMys/3BPEmZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkpOUGZmVkr1vOX7BEnPSHqwUHaNpOn5Mbtyp11JzZJeK0y7tF5xmZlZ/1DPW75fAfwYuLJSEBHHVIYlXQS8VJj/sYgYXcd4zMysH6nnLd/vlNRcbZokAUcDe9Vr+2Zm1r816hrUGGBBRPyzULa5pL9LmippTEcLSjpVUquk1ra2tvpHamZmDdGoBHUcMLkwPh/YNCJ2BD4LTJK0VrUFI2J8RLREREtTU1MfhGpmZo3Q5wlK0srA4cA1lbKIWBwRz+XhacBjwFZ9HZuZmZVHI86g9gEeiYi5lQJJTZKG5OEtgFHA4w2IzczMSqKezcwnA/8LbC1prqRT8qRjWb56D2B3YIak+4HrgdMj4vl6xWZmZuVXz1Z8x3VQfmKVshuAG+oVi5mZ9T/uScLMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzErJCcrMzEqpnnfUnSDpGUkPFsrGSXpK0vT8OLAw7UuSHpU0S9J+9YrLzMz6h3qeQV0B7F+l/OKIGJ0fvweQtC3pVvDb5WUukTSkjrGZmVnJ1S1BRcSdwPM1zn4IcHVELI6IJ4BHgZ3rFZuZmZVfI65BnSlpRq4CXDeXbQzMKcwzN5e9jaRTJbVKam1ra6t3rGZm1iB9naB+CmwJjAbmAxflclWZN6qtICLGR0RLRLQ0NTXVJUgzM2u8Pk1QEbEgIpZGxJvAZSyrxpsLjCzMugkwry9jMzOzcunTBCVpRGH0MKDSwu9m4FhJq0jaHBgF3NuXsZmZWbmsXK8VS5oM7AkMlzQXuADYU9JoUvXdbOA0gIh4SNK1wMPAEuCMiFhar9jMzKz8FFH1Us/bZ5TWiIhFdY6nW1paWqK1tXWF1qFqV7+sz9T48TOzAUzStIhoaV/eZRWfpA9JehiYmcffK+mSOsRoZmb2llquQV0M7Ac8BxAR9wO71zMoMzOzmhpJRMScdkW+PmRmZnVVSyOJOZI+BISkdwBnkav7zMzM6qWWM6jTgTNIPTvMJf3J9ow6xmRmZtb1GVREPAsc3wexmJmZvaWWVnwTJa1TGF9X0oS6RmVmZoNeLVV8O0TEi5WRiHgB2LFuEZmZmVFbglqp0Os4ktajjj1QmJmZQW2J5iLgr5Kuz+NHAd+sX0hmZma1NZK4UlIrsBfpthiHR8TDdY/MzMwGtQ4TlKS1IuLlXKX3NDCpMG29iKj1brlmZmbd1tkZ1CTgIGAay988UHl8izrGZWZmg1yHCSoiDpIkYI+I+FcfxmRmZtZ5K75I9+K4qY9iMTMze0stzczvlrRTd1csaYKkZyQ9WCj7rqRHJM2QdFPlD8CSmiW9Jml6flza3e2ZmdnAUkuC+jApST2WE8sDkmbUsNwVwP7tym4Dto+IHYB/AF8qTHssIkbnx+m1BG9mZgNXLf+DOqAnK46IOyU1tyu7tTB6N3BkT9ZtZmYDX4dnUJI2kPQD4CekHs1fiIgnK49e2PbJwB8K45tL+rukqZLGdBLXqZJaJbW2tbX1QhhmZlZGnVXxXQksAn4EDAN+2FsblfQVYAlwVS6aD2waETsCnwUmSVqr2rIRMT4iWiKipampqbdCMjOzkumsiu+dEfGVPHyLpPt6Y4OSxpL+X7V3biVIRCwGFufhaZIeA7YCWntjm2Zm1v90lqCUO4lVHh9SHO9JTxKS9ge+SPpv1auF8ibg+YhYKmkLYBTweHfXb2ZmA0dnCWptUi8SKpRVzqK67ElC0mRgT2C4pLnABaRWe6sAt6X/AHN3brG3O/A1SUuApcDp7krJzGxw66wnieYVWXFEHFel+OcdzHsDcMOKbM/MzAaWWv4HZWZm1uecoMzMrJScoMzMrJRqSlCSdpN0Uh5ukrR5fcMyM7PBrssEJekCUtPwSr95Q4Ff1TMoMzOzWs6gDgMOJvUqQUTMA9asZ1BmZma1JKg3co8PASBpjfqGZGZmVluCulbSz4B1JH0K+B/gsvqGZWZmg12Xt9uIiO9J+gjwMrA18F8RcVvdIzMzs0GtlvtBkROSk5KZmfWZLhOUpIXk608FL5F6Gv9cRLhTVzMz63W1nEF9H5gHTCJ1HHss8E5gFjCB1CGsmZlZr6qlkcT+EfGziFgYES9HxHjgwIi4Bli3zvGZmdkgVUuCelPS0ZJWyo+jC9PaV/2ZmZn1iloS1PHACcAzwII8/AlJqwFn1jE2MzMbxGppZv448LEOJv+5d8MxMzNLamnFtypwCrAdsGqlPCJO7mK5CcBBwDMRsX0uWw+4BmgGZgNHR8QLedqX8naWAmdFxC3dfzlmZjZQ1FLF90tSq739gKnAJsDCGpa7Ati/Xdl5wO0RMQq4PY8jaVtS68Dt8jKXSBpSwzbMzGyAqiVBvSsivgosioiJwEeB93S1UETcCTzfrvgQYGIenggcWii/OiIWR8QTwKPAzjXEZmZmA1QtCerf+flFSdsDa5Oq6Hpiw4iYD5CfN8jlGwNzCvPNzWVvI+lUSa2SWtva2noYhpmZlV0tCWq8pHWB84GbgYeBb/dyHKpSVrUJe0SMj4iWiGhpamrq5TDMzKwsOm0kIWkl4OXckOFOYIsV3N4CSSMiYr6kEaSm65DOmEYW5tuE1HuFmZkNUp2eQUXEm/Tuf51uBsbm4bHAbwrlx0paJd9OfhRwby9u18zM+pla+uK7TdLnSc3DF1UKI6J9A4jlSJpM6qdvuKS5wAXAhaT7S50C/As4Kq/rIUnXkqoPlwBnRMTS7r8cMzMbKJRultvJDNITVYojIla0um+FtbS0RGtr6wqtQ9Wuflmf6eLjZ2aDgKRpEdHSvryWniQ2r09IZmZmHeuyFZ+k1SWdL2l8Hh8l6aD6h2ZmZoNZLc3MfwG8AXwoj88FvlG3iMzMzKgtQW0ZEd8h/2E3Il6j+v+WzMzMek0trfjeyLfWCABJWwKL6xqVWS9xI5jGc0MY66laEtQ44I/ASElXAbsCJ9YxJjMzs5pa8d0qaRrwAVLV3tkR8WzdIzMzs0GtlvtB3QxMBm6OiEVdzW9mZtYbamkkcREwBnhY0nWSjsw3MTQzM6ubWqr4pgJT8w0E9wI+BUwA1qpzbGZmNojV0kiC3IrvY8AxwPtYdtNBMzOzuqjlGtQ1wC6klnw/AabkXs7NzMzqppYzqF8AH6/0Li5pV0kfj4gz6huamZkNZrVcg/qjpNGSjiNV8T0B3Fj3yMzMbFDrMEFJ2go4FjgOeI50PyhFxIf7KDYzMxvEOjuDegS4C/hYRDwKIOncPonKzMwGvc7+B3UE8DRwh6TLJO1NL3QSK2lrSdMLj5clnSNpnKSnCuUHrui2zMys/+owQUXETRFxDLANMAU4F9hQ0k8l7dvTDUbErIgYHRGjgfcDrwI35ckXV6ZFxO97ug0zM+v/uuxJIiIWRcRVEXEQsAkwHTivl7a/N/BYRDzZS+szM7MBopaujt4SEc9HxM8iYq9e2v6xpH7+Ks6UNEPSBEnrVltA0qmSWiW1trW19VIYZmZWNt1KUL1J0juAg4HrctFPgS2B0cB8Uh+AbxMR4yOiJSJampqa+iJUMzNrgIYlKOAA4L6IWAAQEQsiYmnupeIyYOcGxmZmZg3WyAR1HIXqPUkjCtMOAx7s84jMzKw0auostrdJWh34CHBaofg7kkaTbi0/u900MzMbZBqSoCLiVWD9dmUnNCIWM+vftML/zrQVEVG/dTeyis/MzKxDTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKTlBmZlZKjbph4WxgIbAUWBIRLZLWA64Bmkk3LDw6Il5oRHxmZtZ4jTyD+nBEjI6Iljx+HnB7RIwCbs/jZmY2SJWpiu8QYGIenggc2rhQzMys0RqVoAK4VdI0Safmsg0jYj5Aft6g2oKSTpXUKqm1ra2tj8I1M7O+1pBrUMCuETFP0gbAbZIeqXXBiBgPjAdoaWmJegVoZmaN1ZAzqIiYl5+fAW4CdgYWSBoBkJ+faURsZmZWDn2eoCStIWnNyjCwL/AgcDMwNs82FvhNX8dmZmbl0Ygqvg2BmyRVtj8pIv4o6W/AtZJOAf4FHNWA2MzMrCT6PEFFxOPAe6uUPwfs3dfxmJlZOZWpmbmZmdlbnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUGnHL95GS7pA0U9JDks7O5eMkPSVpen4c2NexmZlZeTTilu9LgM9FxH2S1gSmSbotT7s4Ir7XgJjMzKxkGnHL9/nA/Dy8UNJMYOO+jsPMzMqtodegJDUDOwL35KIzJc2QNEHSuh0sc6qkVkmtbW1tfRWqmZn1sYYlKEnDgBuAcyLiZeCnwJbAaNIZ1kXVlouI8RHREhEtTU1NfRWumZn1sYYkKElDScnpqoi4ESAiFkTE0oh4E7gM2LkRsZmZWTk0ohWfgJ8DMyPi+4XyEYXZDgMe7OvYzMysPBrRim9X4ATgAUnTc9mXgeMkjQYCmA2c1oDYzMysJBrRiu/PgKpM+n1fx2JmZuXlniTMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyUSpegJO0vaZakRyWd1+h4zMysMUqVoCQNAX4CHABsS7oN/LaNjcrMzBqhVAkK2Bl4NCIej4g3gKuBQxock5mZNcDKjQ6gnY2BOYXxucAuxRkknQqcmkdfkTSrj2Irq+HAs40OoqekRkdQev16/4L3cQ369T7upf27WbXCsiWoai81lhuJGA+M75twyk9Sa0S0NDoOqw/v34HP+7hjZavimwuMLIxvAsxrUCxmZtZAZUtQfwNGSdpc0juAY4GbGxyTmZk1QKmq+CJiiaQzgVuAIcCEiHiowWGVnas7Bzbv34HP+7gDioiu5zIzM+tjZaviMzMzA5ygzMyspJyguiBpqaTphUen3S9J2lPShwrjp0v65Apsf5ykz7crmy1peE/X2Y1tT8uNVZC0o6SQtF+Ny54jafX6Rlh/hf3/oKTrOnpNkv7aw/U3S/r4Csb1W0nr9GT7BpK+IukhSTPye7pLLu+r79kUSW9rZp7LZ0m6X9LfJI2udyxl4wTVtdciYnThcWEX8+8JvJWgIuLSiLiy/UySStVApT1JzcBTuUcPgOOAP+fnWpwD9PsExbL9vz3wBnB6cWLunouI+FC1hWvQDHQ7QbWL63ngjB5uf1CT9EHgIOB9EbEDsA/LdxbQ0/X21vf7+Ih4L3AJ8N1eWme/4QTVQ/no6v9Kuk/SA5K2yT/qpwPn5iOxMcUzoHxE9C1JU4GzJb1f0tR8pnKLpBE9iOOz+Sj6QUnn5LJmSY9IujyXXyVpH0l/kfRPSTvn+daQNCEfnf1dUrFbqQOAP+b5BBwJnAjsK2nVdtuZmI8+r5e0uqSzgI2AOyTd0aM3uJzuAt6Vz5LvkDQJeABA0iv5+RpJB1YWkHSFpCPye3VX/rzcVzjLvhAYkz8v50oaIum7eZ/MkHRaDXH9L6kXFiSNlnR3XvYmSet2UT5F0sWS7pQ0U9JOkm7Mn5Nv9NYbV2IjgGcjYjFARDwbEcX/Xn6m+B0HkLSzpL/m78xfJW2dy09UOsv+LXBrR98vSatJujrvi2uA1WqIs7iP15P067z83ZJ26KJ8XP6O3pp/tw6X9J38mv4oaWjvvJV1EBF+dPIAlgLTC49jcvls4DN5+D+By/PwOODzheXfGgemAJfk4aHAX4GmPH4MqVl9++2PA55qF8MbpO5R3k/6gVwDGAY8BOxIOipfAryHdBAyDZhA6qnjEODXed3fAj6Rh9cB/gGskcd/A2yRh3cDbs/Dk4DD83AzqaePXfP4hMJrnQ0Mb/T+64X9/0p+Xjm/J58mnSUvAjavMt9hwMQ8/A7S0fhqpLPJVXP5KKA1D+8J/K6wnlOB8/PwKkBrcTtVtjcEuA7YP4/PAPbIw18DftBF+RTg23n4bNIf40fkbc8F1m/0Pqjz/h2Wv1P/IJ2l7FGYNpvq3/G1gJXz8D7ADXn4xPyerZfHq36/gM+Sv+vADqTvakuV2KZUykk1Et/Kwz8CLsjDewHTuygfR6r9GAq8F3gVOCBPuwk4tNH7oaNHqauZSuK1iBjdwbQb8/M04PAa13dNft4a2B64LZ2gMASY38EyF0fE9yojkmbnwd2AmyJiUS6/ERhD+nPzExFRObp/iJRgQtIDpMQCsC9wsJZd41oV2FTSY8AmEfF4Lj+O1HEv+fmEwmufExF/ycO/As4C3op1AFhN0vQ8fBfwc1IV7r0R8USV+f8A/FDSKsD+wJ0R8ZqktYEfK11HWAps1cH29gV2kHRkHl+blNDab6sSVzPp83db3sY6ETE1zzMRuK6j8sK6Kn+GfwB4KCLmA0h6nNSzy3MdxNrvRcQrkt5P+t58GLhG0nkRcUWepdp3fG1goqRRpAO04hnIbRHxfB6u+v0Cdgd+mLc/Q9KMTkK8StIapN+H9+Wy3YAj8vJ/krR+3scdlQP8ISL+nb//Q8i1I6R93tzpm9RATlArZnF+Xkrt7+Wi/CzSj8EHV2D7nXXTuLgw/GZh/E2WxSrgiIhYrsNdSXuTjrgq11iOIH3RvpKXWV/Smnn29n+kG2h/rHvbAUo+oFhUbeaIeF3SFGA/0lnx5DzpXGAB6Qh2JeD1DrYn0lH7LbXElX+Afke6BjWxqxfTgeJno/3nZsD/RkTEUtLZypT8Az4WuCJPrvYd/zpwR0QcplStP6WwuuLnoqPvF9T+PTkeuJ9UFfwTUpLsqM/SzvoyrVRhvinp35FPnyj5PvY1qN63EFizy7lgFtCkdJEWSUMlbdfNbd0JHJqv+6xBql66qxvL30KqY1eOYcdcvj/pTABSFcb9ETEyIpojYjPgBuDQPH3TymtgWUMKqP19GIiuBk4iHZVXEs3awPyIeJN0Bjokl7d/n24BPl25LiBpq7xvq4qIl0hnrZ8nVd28IGlMnnwCMDXP87byFXuJA4OkrfOZUMVo4MkuFlubVO0OqVqvIx19v+4kJR4kbU+q5utQRPwbOB/4gKR3t1t+T9I1tJc7Ke+3nKC6tpqWb2beVSu+3wKH5XnHdDRTpNZxRwLflnQ/qR68Wy3BIuI+0pHevcA9pDryv3djFV8nVU/MkPRgHod0XaTyA3YcqZ666AaWtTybCYzN1RTrAT/N5eOBP2hgNZKo1a2kapz/iWWtIC8hvU93k6r3KkfaM4AlSk2JzwUuBx4G7sv75Gd0cYSb9/n9pL4rxwLfzftjNOl6E52UD3bDSNV1D+f3ZlvSNZvOfAf4f5L+wrIDjWo6+n79FBiWt/cF0ve3UxHxGnAR6UBkHNCSl7+QtG/ppLzfcldHthxJmwCXRcQBNczbTLrAv33dAzOzQae0dY/WGBExl9TE3MysoXwGZWZmpeRrUGZmVkpOUGZmVkpOUGZmVkpuJGHWQ5KWkv6JvzKpp4cTIuLFPtjuPaSuiNYjdaNU+U/OoRExu97bN+srbiRh1kOSXomIYXl4IvCPiPhmH27/RFJfbWf21TbN+pKr+Mx6R8N6FJe0Up63qTD+qKThSr2pX6rUk/o/JB2U5+lJr+lmfcoJymwF5f4K92ZZp6tXAl+MdH+hB4ALuigHeCMidgcuJfWafgapM+ETJa3f2fZz90m/Indzw7LuqZ7N483AHsBHgUuVbpdyCvBSROwE7AR8StLmPXj5ZnXjBGXWc5UexZ8jXQ/qqEfx3TsqL6zrbT2KR7pHUaVH8a5MACp3bj4Z+EVh2rUR8WZE/DOvbxtST9ufzPHfA6xP6jXdrDScoMx6rtLT+Wakez+tyF1tV6hH8YiYAyyQtBewC8s6+4XqPc5Xek0fnR+bR8StPY7erA6coMxWUIl6FL+cVNV3bb6FRMVR+brUlsAWpJ70u9VrulkjuJm5WS+IiL/nXukrPYpfKml1UpXaSXm2jsp7y82kqr1ftCufRUqGGwKn53tWXU66NnVfvh1EG8tuoWJWCm5mbjZASGoh3X15TKHsClKP89c3LDCzHvIZlNkAIOk84NMsa8ln1u/5DMrMzErJjSTMzKyUnKDMzKyUnKDMzKyUnKDMzKyUnKDMzKyU/j/2aszylvsrWAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.bar(room_type, average_price, color='b')\n",
    "\n",
    "plt.xlabel(\"Room Type\")\n",
    "plt.ylabel(\"Average Price\")\n",
    "plt.title(\"Room Type vs Average Price Comparison\")\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 274,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 432x288 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.savefig(\"price comparison\")"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}