Are Airbnb guests less energy efficient than their host?

dataset.csv

dataset.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Are Airbnb guests less energy efficient than their host?"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Building a dataset"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Host"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import datetime as dt\n",
    "\n",
    "hosts = pd.DataFrame(\n",
    "    [\n",
    "        (dt.date(2022, 2, 17), dt.date(2022, 2, 19), 2),  \n",
    "        (dt.date(2022, 2, 26), dt.date(2022, 3, 1), 2),  \n",
    "        (dt.date(2022, 3, 19), dt.date(2022, 3, 23), 1),  \n",
    "        (dt.date(2022, 3, 26), dt.date(2022, 3, 30), 2),  \n",
    "        (dt.date(2022, 6, 17), dt.date(2022, 6, 20), 2),  \n",
    "        (dt.date(2022, 7, 6), dt.date(2022, 7, 10), 1),  \n",
    "        (dt.date(2022, 7, 29), dt.date(2022, 7, 29), 1),  \n",
    "        (dt.date(2022, 8, 1), dt.date(2022, 8, 3), 2),  \n",
    "        (dt.date(2022, 11, 17), dt.date(2022, 11, 19), 1),  \n",
    "        (dt.date(2022, 11, 21), dt.date(2022, 11, 25), 1),  \n",
    "        (dt.date(2022, 11, 26), dt.date(2022, 12, 2), 1),  \n",
    "        (dt.date(2022, 12, 2), dt.date(2022, 12, 3), 2),  \n",
    "        (dt.date(2022, 12, 4), dt.date(2022, 12, 8), 2),  \n",
    "        (dt.date(2022, 12, 12), dt.date(2022, 12, 17), 2),  \n",
    "        (dt.date(2022, 12, 21), dt.date(2022, 12, 23), 2),  \n",
    "        (dt.date(2022, 12, 23), dt.date(2022, 12, 25), 1),  \n",
    "    ],\n",
    "    columns=[\"since\", \"until\", \"n_hosts\"],\n",
    ")\n",
    "hosts.to_csv(\"hosts.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "date\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">02</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">18</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2.0</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">02</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">26</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.0</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">03</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">23</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.5</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">07</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">29</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.5</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">29</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.0</span>\n",
       "Name: n_hosts, dtype: float64\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "date\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m02\u001b[0m-\u001b[1;36m18\u001b[0m    \u001b[1;36m2.0\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m02\u001b[0m-\u001b[1;36m26\u001b[0m    \u001b[1;36m1.0\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m03\u001b[0m-\u001b[1;36m23\u001b[0m    \u001b[1;36m0.5\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m07\u001b[0m-\u001b[1;36m29\u001b[0m    \u001b[1;36m0.5\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m11\u001b[0m-\u001b[1;36m29\u001b[0m    \u001b[1;36m1.0\u001b[0m\n",
       "Name: n_hosts, dtype: float64\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "host_dates = pd.concat([\n",
    "    pd.DataFrame({\n",
    "        \"date\": (dates := pd.date_range(stay[\"since\"], stay[\"until\"], inclusive=\"both\", freq=\"D\")),\n",
    "        # We count only 50% for start and end days, because people don't spend the whole day there\n",
    "        \"n_hosts\": (\n",
    "            [stay[\"n_hosts\"] / 2] +\n",
    "            [stay[\"n_hosts\"]] * (len(dates) - 2) +\n",
    "            ([stay[\"n_hosts\"] / 2] if len(dates) > 1 else [])\n",
    "        )\n",
    "    })\n",
    "    for stay in hosts.to_dict(orient=\"records\")\n",
    "])\n",
    "host_dates = host_dates.groupby(\"date\")[\"n_hosts\"].sum()\n",
    "host_dates.sample(5)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### kW/h"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>kilowatt-hour</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2022-09-05</th>\n",
       "      <td>2.749</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-18</th>\n",
       "      <td>26.668</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-10-10</th>\n",
       "      <td>4.343</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-07-14</th>\n",
       "      <td>3.217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-07-09</th>\n",
       "      <td>3.281</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import glob\n",
    "import pandas as pd\n",
    "\n",
    "kwh = (\n",
    "    pd.concat([\n",
    "        pd.read_csv(p, parse_dates=[\"Date\"], dayfirst=True)\n",
    "        for p in glob.glob(\"data/historique*.csv\")\n",
    "    ])\n",
    "    .rename(columns={\"Date\": \"date\", \"Conso en kWh\": \"kilowatt-hour\"})\n",
    "    .set_index(\"date\")\n",
    ")\n",
    "kwh.sample(5)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Guests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>Confirmation code</th>\n",
       "      <th>Status</th>\n",
       "      <th># of guests</th>\n",
       "      <th>Start date</th>\n",
       "      <th>End date</th>\n",
       "      <th># of nights</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>HMM29JP58P</td>\n",
       "      <td>Past guest</td>\n",
       "      <td>1</td>\n",
       "      <td>2022-01-02</td>\n",
       "      <td>2022-01-12</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>HM34P8THWE</td>\n",
       "      <td>Past guest</td>\n",
       "      <td>1</td>\n",
       "      <td>2022-01-13</td>\n",
       "      <td>2022-02-12</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>HMMJH8NSHQ</td>\n",
       "      <td>Past guest</td>\n",
       "      <td>1</td>\n",
       "      <td>2022-02-19</td>\n",
       "      <td>2022-02-25</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>HM93S8EPCM</td>\n",
       "      <td>Past guest</td>\n",
       "      <td>1</td>\n",
       "      <td>2022-03-07</td>\n",
       "      <td>2022-03-17</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>HMHMMNSW25</td>\n",
       "      <td>Past guest</td>\n",
       "      <td>1</td>\n",
       "      <td>2022-04-07</td>\n",
       "      <td>2022-06-01</td>\n",
       "      <td>55</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "guests = pd.read_csv('data/guests.csv', parse_dates=[\"Start date\", \"End date\"])\n",
    "(\n",
    "    pd.concat([\n",
    "        guests[[\"Start date\", \"End date\"]],\n",
    "        pd.DataFrame([\n",
    "            {\"Start date\": pd.Timestamp('2022-12-27 00:00:00'), \"End date\": pd.Timestamp('2022-12-31 00:00:00')},\n",
    "        ], index=[len(guests)])\n",
    "    ])\n",
    "    .rename(columns={\"Start date\": \"since\", \"End date\": \"until\"})\n",
    "    .to_csv('guests.csv')\n",
    ")\n",
    "guests[\"# of guests\"] = guests[\"# of adults\"] + guests[\"# of children\"] + guests[\"# of infants\"]\n",
    "guests[['Confirmation code', 'Status', '# of guests', 'Start date', 'End date', '# of nights']].head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "date\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">06</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">08</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.0</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">08</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2.0</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">05</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">28</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.0</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">01</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">22</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.0</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">04</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">08</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.0</span>\n",
       "Name: n_guests, dtype: float64\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "date\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m06\u001b[0m-\u001b[1;36m08\u001b[0m    \u001b[1;36m1.0\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m08\u001b[0m-\u001b[1;36m11\u001b[0m    \u001b[1;36m2.0\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m05\u001b[0m-\u001b[1;36m28\u001b[0m    \u001b[1;36m1.0\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m01\u001b[0m-\u001b[1;36m22\u001b[0m    \u001b[1;36m1.0\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m04\u001b[0m-\u001b[1;36m08\u001b[0m    \u001b[1;36m1.0\u001b[0m\n",
       "Name: n_guests, dtype: float64\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "guest_dates = pd.concat([\n",
    "    pd.DataFrame({\n",
    "        \"date\": (dates := pd.date_range(stay[\"Start date\"], stay[\"End date\"], inclusive=\"both\", freq=\"D\")),\n",
    "        # We count only 50% for start and end days, because people don't spend the whole day there\n",
    "        \"n_guests\": (\n",
    "            [stay[\"# of guests\"] / 2] +\n",
    "            [stay[\"# of guests\"]] * (len(dates) - 2) +\n",
    "            ([stay[\"# of guests\"] / 2] if len(dates) > 1 else [])\n",
    "        )\n",
    "    })\n",
    "    for stay in guests.to_dict(orient=\"records\")\n",
    "])\n",
    "guest_dates = guest_dates.groupby(\"date\")[\"n_guests\"].sum()\n",
    "\n",
    "# Early guest who should have arrived in 2023\n",
    "guest_dates.loc[pd.Timestamp('2022-12-27 00:00:00')] = 0.5\n",
    "guest_dates.loc[pd.Timestamp('2022-12-28 00:00:00')] = 1\n",
    "guest_dates.loc[pd.Timestamp('2022-12-29 00:00:00')] = 1\n",
    "guest_dates.loc[pd.Timestamp('2022-12-30 00:00:00')] = 1\n",
    "guest_dates.loc[pd.Timestamp('2022-12-31 00:00:00')] = 1\n",
    "\n",
    "guest_dates.sample(5)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Weather"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "date\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">08</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">09</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">27.7875</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">10</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">04</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">17.7750</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">14.5250</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">12</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">19</span>    <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">12.9625</span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2022</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">01</span>-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">10</span>     <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">7.8375</span>\n",
       "Name: temperature, dtype: float64\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "date\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m08\u001b[0m-\u001b[1;36m09\u001b[0m    \u001b[1;36m27.7875\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m10\u001b[0m-\u001b[1;36m04\u001b[0m    \u001b[1;36m17.7750\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m11\u001b[0m-\u001b[1;36m11\u001b[0m    \u001b[1;36m14.5250\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m12\u001b[0m-\u001b[1;36m19\u001b[0m    \u001b[1;36m12.9625\u001b[0m\n",
       "\u001b[1;36m2022\u001b[0m-\u001b[1;36m01\u001b[0m-\u001b[1;36m10\u001b[0m     \u001b[1;36m7.8375\u001b[0m\n",
       "Name: temperature, dtype: float64\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "weather = (\n",
    "    pd.read_csv(\n",
    "        'data/donnees-synop-essentielles-omm.csv',\n",
    "        sep=';',\n",
    "        parse_dates=[\"Date\"],\n",
    "        date_parser=lambda x: pd.to_datetime(x, utc=True)\n",
    "    )\n",
    "    .rename(columns={'Date': 'datetime', \"Température (°C)\": 'temperature'})\n",
    "    .assign(date=lambda df: df['datetime'].dt.date)\n",
    ")\n",
    "temperature = weather.groupby('date')['temperature'].mean()\n",
    "temperature = temperature[temperature.index.map(lambda d: d.year == 2022)]\n",
    "temperature.sample(5)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Join them all"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>date</th>\n",
       "      <th>kilowatt-hour</th>\n",
       "      <th>n_hosts</th>\n",
       "      <th>n_guests</th>\n",
       "      <th>temperature</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2022-01-01</td>\n",
       "      <td>2.171</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.8750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2022-01-02</td>\n",
       "      <td>10.310</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>8.7875</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2022-01-03</td>\n",
       "      <td>16.107</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.3500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2022-01-04</td>\n",
       "      <td>16.563</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9.2500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2022-01-05</td>\n",
       "      <td>17.098</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5.7000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset = (\n",
    "    kwh\n",
    "    .join(host_dates)\n",
    "    .join(guest_dates)\n",
    "    .join(temperature)\n",
    ")\n",
    "dataset = dataset.sort_index().reset_index()\n",
    "dataset.n_hosts = dataset.n_hosts.fillna(0).astype(float)\n",
    "dataset.n_guests = dataset.n_guests.fillna(0).astype(float)\n",
    "dataset.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">365</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1;36m365\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "len(dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset.to_csv('dataset.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "| date                |   kilowatt-hour |   n_hosts |   n_guests |   temperature |\n",
      "|:--------------------|----------------:|----------:|-----------:|--------------:|\n",
      "| 2022-01-01 00:00:00 |           2.171 |         0 |        0   |        7.875  |\n",
      "| 2022-01-02 00:00:00 |          10.31  |         0 |        0.5 |        8.7875 |\n",
      "| 2022-01-03 00:00:00 |          16.107 |         0 |        1   |        8.35   |\n",
      "| 2022-01-04 00:00:00 |          16.563 |         0 |        1   |        9.25   |\n",
      "| 2022-01-05 00:00:00 |          17.098 |         0 |        1   |        5.7    |\n"
     ]
    }
   ],
   "source": [
    "print(dataset.head().to_markdown(index=False))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Regression analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "hourly_temperatures = (\n",
    "    weather\n",
    "    .sort_values('datetime')\n",
    "    .set_index('datetime')\n",
    "    ['temperature']\n",
    "    .resample('1H')\n",
    "    .mean()\n",
    "    .interpolate()\n",
    ")\n",
    "reference_temperature = 18\n",
    "heating_degree_days = (\n",
    "    hourly_temperatures\n",
    "    .apply(lambda t: max(0, reference_temperature - t))\n",
    "    .to_frame()\n",
    "    .assign(date=lambda df: df.index.date)\n",
    "    .groupby('date')\n",
    "    .sum()\n",
    "    .rename(columns={'temperature': 'heating_degree_days'})\n",
    ")\n",
    "cooling_degree_days = (\n",
    "    hourly_temperatures\n",
    "    .apply(lambda t: max(0, t - reference_temperature))\n",
    "    .to_frame()\n",
    "    .assign(date=lambda df: df.index.date)\n",
    "    .groupby('date')\n",
    "    .sum()\n",
    "    .rename(columns={'temperature': 'cooling_degree_days'})\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>is_weekend</th>\n",
       "      <th>n_people</th>\n",
       "      <th>is_guest</th>\n",
       "      <th>heating_degree_days</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2022-01-01</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>244.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-02</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>219.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-03</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>231.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-04</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>208.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-05</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>301.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = (\n",
    "    dataset\n",
    "    .set_index('date')\n",
    "    .join(heating_degree_days)\n",
    "    .join(cooling_degree_days)\n",
    "    .reset_index()\n",
    ")\n",
    "X['is_weekend'] = X.date.dt.dayofweek > 4\n",
    "X['n_people'] = X.n_hosts + X.n_guests\n",
    "X['is_guest'] = X.n_guests > 0\n",
    "X = X.set_index('date')[[\n",
    "    'is_weekend',\n",
    "    'n_people',\n",
    "    'is_guest',\n",
    "    'heating_degree_days'\n",
    "]].astype(float)\n",
    "y = dataset.set_index('date')['kilowatt-hour']\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                 OLS Regression Results                                \n",
      "=======================================================================================\n",
      "Dep. Variable:          kilowatt-hour   R-squared (uncentered):                   0.844\n",
      "Model:                            OLS   Adj. R-squared (uncentered):              0.843\n",
      "Method:                 Least Squares   F-statistic:                              489.2\n",
      "Date:                Tue, 17 Jan 2023   Prob (F-statistic):                   2.61e-144\n",
      "Time:                        17:46:00   Log-Likelihood:                         -1011.5\n",
      "No. Observations:                 365   AIC:                                      2031.\n",
      "Df Residuals:                     361   BIC:                                      2047.\n",
      "Df Model:                           4                                                  \n",
      "Covariance Type:            nonrobust                                                  \n",
      "=======================================================================================\n",
      "                          coef    std err          t      P>|t|      [0.025      0.975]\n",
      "---------------------------------------------------------------------------------------\n",
      "is_weekend             -1.5339      0.435     -3.527      0.000      -2.389      -0.679\n",
      "n_people                2.4652      0.331      7.455      0.000       1.815       3.116\n",
      "is_guest                1.7145      0.451      3.798      0.000       0.827       2.602\n",
      "heating_degree_days     0.0405      0.001     27.288      0.000       0.038       0.043\n",
      "==============================================================================\n",
      "Omnibus:                        6.854   Durbin-Watson:                   0.729\n",
      "Prob(Omnibus):                  0.032   Jarque-Bera (JB):                9.520\n",
      "Skew:                           0.120   Prob(JB):                      0.00856\n",
      "Kurtosis:                       3.754   Cond. No.                         425.\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] R² is computed without centering (uncentered) since the model does not contain a constant.\n",
      "[2] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "\n",
    "mod = sm.OLS(y, X)\n",
    "res = mod.fit()\n",
    "print(res.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.972</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1;36m0.972\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "24 * 0.0405"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.11.0 64-bit ('3.11.0')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.0"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "55fbbcf542e06cc59ad76a1e0d5dc36ee204d6d2b704491656ee6b3487310122"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}