{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# `GPflow` Gaussian Process Model of the Polydome Building"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Base math/data packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Gaussian Process Modeling packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gpflow\n",
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from gpflow.utilities import print_summary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Print summary in notebook format:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "gpflow.config.set_default_summary_fmt(\"notebook\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "#tf.config.set_visible_devices([], 'GPU')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plotting package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notebook output parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "plt.rcParams[\"figure.figsize\"] = (12, 6)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Enable horizontal scroll for print output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>pre { white-space: pre !important; }</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from IPython.core.display import HTML\n",
    "display(HTML(\"<style>pre { white-space: pre !important; }</style>\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data pre-processing"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load the Experimental measurements to fit a GP model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Experiments used for identification: 7 6 4 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Experiments used for validation: 3 5 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "exp_id = 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>time</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>zenith</th>\n",
       "      <th>azimuth</th>\n",
       "      <th>dni</th>\n",
       "      <th>dhi</th>\n",
       "      <th>OutsideTemp</th>\n",
       "      <th>Tsky_rad</th>\n",
       "      <th>relative_humidity</th>\n",
       "      <th>precipitation</th>\n",
       "      <th>cloud_index</th>\n",
       "      <th>pressure</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_direction</th>\n",
       "      <th>aoi</th>\n",
       "      <th>incidence_main</th>\n",
       "      <th>incidence_second</th>\n",
       "      <th>poa_direct</th>\n",
       "      <th>poa_diffuse</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>201706012000</td>\n",
       "      <td>78.691622</td>\n",
       "      <td>290.430819</td>\n",
       "      <td>7.251337</td>\n",
       "      <td>59.908644</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>78.691622</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>1.421911</td>\n",
       "      <td>59.908644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>300</td>\n",
       "      <td>201706012005</td>\n",
       "      <td>79.489651</td>\n",
       "      <td>291.279501</td>\n",
       "      <td>7.672114</td>\n",
       "      <td>56.537088</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>79.489651</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>1.399494</td>\n",
       "      <td>56.537088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>600</td>\n",
       "      <td>201706012010</td>\n",
       "      <td>80.282334</td>\n",
       "      <td>292.130503</td>\n",
       "      <td>8.423139</td>\n",
       "      <td>53.492674</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>80.282334</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>1.421769</td>\n",
       "      <td>53.492674</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>900</td>\n",
       "      <td>201706012015</td>\n",
       "      <td>81.069332</td>\n",
       "      <td>292.984123</td>\n",
       "      <td>52.657244</td>\n",
       "      <td>65.770239</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>81.069332</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>8.174467</td>\n",
       "      <td>65.770239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1200</td>\n",
       "      <td>201706012020</td>\n",
       "      <td>81.850261</td>\n",
       "      <td>293.840653</td>\n",
       "      <td>94.364403</td>\n",
       "      <td>62.829177</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>81.850261</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>13.377157</td>\n",
       "      <td>62.829177</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>535</th>\n",
       "      <td>160500</td>\n",
       "      <td>201706031635</td>\n",
       "      <td>43.923091</td>\n",
       "      <td>252.722275</td>\n",
       "      <td>64.970386</td>\n",
       "      <td>314.462614</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>43.923091</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>46.796324</td>\n",
       "      <td>314.462614</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>536</th>\n",
       "      <td>160800</td>\n",
       "      <td>201706031640</td>\n",
       "      <td>44.746130</td>\n",
       "      <td>253.882437</td>\n",
       "      <td>530.910153</td>\n",
       "      <td>219.485890</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>44.746130</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>377.069871</td>\n",
       "      <td>219.485890</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>537</th>\n",
       "      <td>161100</td>\n",
       "      <td>201706031645</td>\n",
       "      <td>45.573942</td>\n",
       "      <td>255.018953</td>\n",
       "      <td>428.243363</td>\n",
       "      <td>250.653973</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>45.573942</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>299.765305</td>\n",
       "      <td>250.653973</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>161400</td>\n",
       "      <td>201706031650</td>\n",
       "      <td>46.406107</td>\n",
       "      <td>256.133161</td>\n",
       "      <td>667.400308</td>\n",
       "      <td>167.328816</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>46.406107</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>460.200780</td>\n",
       "      <td>167.328816</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>161700</td>\n",
       "      <td>201706031655</td>\n",
       "      <td>47.242228</td>\n",
       "      <td>257.226338</td>\n",
       "      <td>514.333795</td>\n",
       "      <td>215.275641</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>0.5</td>\n",
       "      <td>96300</td>\n",
       "      <td>0</td>\n",
       "      <td>-9999</td>\n",
       "      <td>47.242228</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>349.181391</td>\n",
       "      <td>215.275641</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>540 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       time     timestamp     zenith     azimuth         dni         dhi  \\\n",
       "0         0  201706012000  78.691622  290.430819    7.251337   59.908644   \n",
       "1       300  201706012005  79.489651  291.279501    7.672114   56.537088   \n",
       "2       600  201706012010  80.282334  292.130503    8.423139   53.492674   \n",
       "3       900  201706012015  81.069332  292.984123   52.657244   65.770239   \n",
       "4      1200  201706012020  81.850261  293.840653   94.364403   62.829177   \n",
       "..      ...           ...        ...         ...         ...         ...   \n",
       "535  160500  201706031635  43.923091  252.722275   64.970386  314.462614   \n",
       "536  160800  201706031640  44.746130  253.882437  530.910153  219.485890   \n",
       "537  161100  201706031645  45.573942  255.018953  428.243363  250.653973   \n",
       "538  161400  201706031650  46.406107  256.133161  667.400308  167.328816   \n",
       "539  161700  201706031655  47.242228  257.226338  514.333795  215.275641   \n",
       "\n",
       "     OutsideTemp  Tsky_rad  relative_humidity  precipitation  cloud_index  \\\n",
       "0           22.0      16.0                 50          -9999          0.5   \n",
       "1           22.0      16.0                 50          -9999          0.5   \n",
       "2           22.0      16.0                 50          -9999          0.5   \n",
       "3           22.0      16.0                 50          -9999          0.5   \n",
       "4           22.0      16.0                 50          -9999          0.5   \n",
       "..           ...       ...                ...            ...          ...   \n",
       "535         24.0      18.0                 50          -9999          0.5   \n",
       "536         24.0      18.0                 50          -9999          0.5   \n",
       "537         24.0      18.0                 50          -9999          0.5   \n",
       "538         24.0      18.0                 50          -9999          0.5   \n",
       "539         24.0      18.0                 50          -9999          0.5   \n",
       "\n",
       "     pressure  wind_speed  wind_direction        aoi  incidence_main  \\\n",
       "0       96300           0           -9999  78.691622           -9999   \n",
       "1       96300           0           -9999  79.489651           -9999   \n",
       "2       96300           0           -9999  80.282334           -9999   \n",
       "3       96300           0           -9999  81.069332           -9999   \n",
       "4       96300           0           -9999  81.850261           -9999   \n",
       "..        ...         ...             ...        ...             ...   \n",
       "535     96300           0           -9999  43.923091           -9999   \n",
       "536     96300           0           -9999  44.746130           -9999   \n",
       "537     96300           0           -9999  45.573942           -9999   \n",
       "538     96300           0           -9999  46.406107           -9999   \n",
       "539     96300           0           -9999  47.242228           -9999   \n",
       "\n",
       "     incidence_second  poa_direct  poa_diffuse  \n",
       "0               -9999    1.421911    59.908644  \n",
       "1               -9999    1.399494    56.537088  \n",
       "2               -9999    1.421769    53.492674  \n",
       "3               -9999    8.174467    65.770239  \n",
       "4               -9999   13.377157    62.829177  \n",
       "..                ...         ...          ...  \n",
       "535             -9999   46.796324   314.462614  \n",
       "536             -9999  377.069871   219.485890  \n",
       "537             -9999  299.765305   250.653973  \n",
       "538             -9999  460.200780   167.328816  \n",
       "539             -9999  349.181391   215.275641  \n",
       "\n",
       "[540 rows x 19 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_wdb = pd.read_pickle(f\"../Data/Experimental_python/Exp{exp_id}_WDB.pkl\")\n",
    "df_wdb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_carnot = pd.read_pickle(f\"../Data/CARNOT_output/Exp{exp_id}_full.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_data = df_carnot.loc[:, ['Power', 'Setpoint', 'OutsideTemp', 'SupplyTemp', 'InsideTemp', 'SolRad']]\n",
    "df_simulated = df_carnot.loc[:, 'SimulatedTemp']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "plt.plot(df_data.index, df_data['OutsideTemp'], label = 'Outside Temperature')\n",
    "plt.plot(df_data.index, df_data['InsideTemp'], label = 'Inside Temperature')\n",
    "plt.plot(df_simulated.index, df_simulated, label = 'Simulated Temperature')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Combine the different dataframes into one"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.concat([df_wdb, df_data.reset_index(), df_simulated.reset_index()], axis = 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Drop duplicated columns:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.loc[:,~df.columns.duplicated()]"
   ]
  },
  {
   "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>time</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>zenith</th>\n",
       "      <th>azimuth</th>\n",
       "      <th>dni</th>\n",
       "      <th>dhi</th>\n",
       "      <th>OutsideTemp</th>\n",
       "      <th>Tsky_rad</th>\n",
       "      <th>relative_humidity</th>\n",
       "      <th>precipitation</th>\n",
       "      <th>...</th>\n",
       "      <th>incidence_main</th>\n",
       "      <th>incidence_second</th>\n",
       "      <th>poa_direct</th>\n",
       "      <th>poa_diffuse</th>\n",
       "      <th>Power</th>\n",
       "      <th>Setpoint</th>\n",
       "      <th>SupplyTemp</th>\n",
       "      <th>InsideTemp</th>\n",
       "      <th>SolRad</th>\n",
       "      <th>SimulatedTemp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>201706012000</td>\n",
       "      <td>78.691622</td>\n",
       "      <td>290.430819</td>\n",
       "      <td>7.251337</td>\n",
       "      <td>59.908644</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>1.421911</td>\n",
       "      <td>59.908644</td>\n",
       "      <td>4325.034483</td>\n",
       "      <td>23.5</td>\n",
       "      <td>24.5</td>\n",
       "      <td>24.300000</td>\n",
       "      <td>61.321333</td>\n",
       "      <td>23.639075</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>300</td>\n",
       "      <td>201706012005</td>\n",
       "      <td>79.489651</td>\n",
       "      <td>291.279501</td>\n",
       "      <td>7.672114</td>\n",
       "      <td>56.537088</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>1.399494</td>\n",
       "      <td>56.537088</td>\n",
       "      <td>4287.000000</td>\n",
       "      <td>23.5</td>\n",
       "      <td>15.5</td>\n",
       "      <td>24.283333</td>\n",
       "      <td>57.926100</td>\n",
       "      <td>23.243140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>600</td>\n",
       "      <td>201706012010</td>\n",
       "      <td>80.282334</td>\n",
       "      <td>292.130503</td>\n",
       "      <td>8.423139</td>\n",
       "      <td>53.492674</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>1.421769</td>\n",
       "      <td>53.492674</td>\n",
       "      <td>4319.766667</td>\n",
       "      <td>23.5</td>\n",
       "      <td>15.2</td>\n",
       "      <td>24.083333</td>\n",
       "      <td>54.902033</td>\n",
       "      <td>23.335477</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>900</td>\n",
       "      <td>201706012015</td>\n",
       "      <td>81.069332</td>\n",
       "      <td>292.984123</td>\n",
       "      <td>52.657244</td>\n",
       "      <td>65.770239</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>8.174467</td>\n",
       "      <td>65.770239</td>\n",
       "      <td>2893.344828</td>\n",
       "      <td>23.5</td>\n",
       "      <td>14.9</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>73.860700</td>\n",
       "      <td>23.524368</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1200</td>\n",
       "      <td>201706012020</td>\n",
       "      <td>81.850261</td>\n",
       "      <td>293.840653</td>\n",
       "      <td>94.364403</td>\n",
       "      <td>62.829177</td>\n",
       "      <td>22.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>13.377157</td>\n",
       "      <td>62.829177</td>\n",
       "      <td>59.137931</td>\n",
       "      <td>23.5</td>\n",
       "      <td>18.2</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>76.042533</td>\n",
       "      <td>23.793051</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>535</th>\n",
       "      <td>160500</td>\n",
       "      <td>201706031635</td>\n",
       "      <td>43.923091</td>\n",
       "      <td>252.722275</td>\n",
       "      <td>64.970386</td>\n",
       "      <td>314.462614</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>46.796324</td>\n",
       "      <td>314.462614</td>\n",
       "      <td>62.137931</td>\n",
       "      <td>24.5</td>\n",
       "      <td>16.4</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>361.247267</td>\n",
       "      <td>24.062549</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>536</th>\n",
       "      <td>160800</td>\n",
       "      <td>201706031640</td>\n",
       "      <td>44.746130</td>\n",
       "      <td>253.882437</td>\n",
       "      <td>530.910153</td>\n",
       "      <td>219.485890</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>377.069871</td>\n",
       "      <td>219.485890</td>\n",
       "      <td>57.482759</td>\n",
       "      <td>24.5</td>\n",
       "      <td>17.6</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>596.456167</td>\n",
       "      <td>24.158706</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>537</th>\n",
       "      <td>161100</td>\n",
       "      <td>201706031645</td>\n",
       "      <td>45.573942</td>\n",
       "      <td>255.018953</td>\n",
       "      <td>428.243363</td>\n",
       "      <td>250.653973</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>299.765305</td>\n",
       "      <td>250.653973</td>\n",
       "      <td>56.233333</td>\n",
       "      <td>24.5</td>\n",
       "      <td>18.5</td>\n",
       "      <td>22.316667</td>\n",
       "      <td>550.335400</td>\n",
       "      <td>24.269707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>161400</td>\n",
       "      <td>201706031650</td>\n",
       "      <td>46.406107</td>\n",
       "      <td>256.133161</td>\n",
       "      <td>667.400308</td>\n",
       "      <td>167.328816</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>460.200780</td>\n",
       "      <td>167.328816</td>\n",
       "      <td>53.379310</td>\n",
       "      <td>24.5</td>\n",
       "      <td>20.0</td>\n",
       "      <td>22.450000</td>\n",
       "      <td>627.393133</td>\n",
       "      <td>24.348123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>161700</td>\n",
       "      <td>201706031655</td>\n",
       "      <td>47.242228</td>\n",
       "      <td>257.226338</td>\n",
       "      <td>514.333795</td>\n",
       "      <td>215.275641</td>\n",
       "      <td>24.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>50</td>\n",
       "      <td>-9999</td>\n",
       "      <td>...</td>\n",
       "      <td>-9999</td>\n",
       "      <td>-9999</td>\n",
       "      <td>349.181391</td>\n",
       "      <td>215.275641</td>\n",
       "      <td>58.379310</td>\n",
       "      <td>24.5</td>\n",
       "      <td>23.3</td>\n",
       "      <td>22.700000</td>\n",
       "      <td>564.347267</td>\n",
       "      <td>24.393026</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>540 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       time     timestamp     zenith     azimuth         dni         dhi  \\\n",
       "0         0  201706012000  78.691622  290.430819    7.251337   59.908644   \n",
       "1       300  201706012005  79.489651  291.279501    7.672114   56.537088   \n",
       "2       600  201706012010  80.282334  292.130503    8.423139   53.492674   \n",
       "3       900  201706012015  81.069332  292.984123   52.657244   65.770239   \n",
       "4      1200  201706012020  81.850261  293.840653   94.364403   62.829177   \n",
       "..      ...           ...        ...         ...         ...         ...   \n",
       "535  160500  201706031635  43.923091  252.722275   64.970386  314.462614   \n",
       "536  160800  201706031640  44.746130  253.882437  530.910153  219.485890   \n",
       "537  161100  201706031645  45.573942  255.018953  428.243363  250.653973   \n",
       "538  161400  201706031650  46.406107  256.133161  667.400308  167.328816   \n",
       "539  161700  201706031655  47.242228  257.226338  514.333795  215.275641   \n",
       "\n",
       "     OutsideTemp  Tsky_rad  relative_humidity  precipitation  ...  \\\n",
       "0           22.0      16.0                 50          -9999  ...   \n",
       "1           22.0      16.0                 50          -9999  ...   \n",
       "2           22.0      16.0                 50          -9999  ...   \n",
       "3           22.0      16.0                 50          -9999  ...   \n",
       "4           22.0      16.0                 50          -9999  ...   \n",
       "..           ...       ...                ...            ...  ...   \n",
       "535         24.0      18.0                 50          -9999  ...   \n",
       "536         24.0      18.0                 50          -9999  ...   \n",
       "537         24.0      18.0                 50          -9999  ...   \n",
       "538         24.0      18.0                 50          -9999  ...   \n",
       "539         24.0      18.0                 50          -9999  ...   \n",
       "\n",
       "     incidence_main  incidence_second  poa_direct  poa_diffuse        Power  \\\n",
       "0             -9999             -9999    1.421911    59.908644  4325.034483   \n",
       "1             -9999             -9999    1.399494    56.537088  4287.000000   \n",
       "2             -9999             -9999    1.421769    53.492674  4319.766667   \n",
       "3             -9999             -9999    8.174467    65.770239  2893.344828   \n",
       "4             -9999             -9999   13.377157    62.829177    59.137931   \n",
       "..              ...               ...         ...          ...          ...   \n",
       "535           -9999             -9999   46.796324   314.462614    62.137931   \n",
       "536           -9999             -9999  377.069871   219.485890    57.482759   \n",
       "537           -9999             -9999  299.765305   250.653973    56.233333   \n",
       "538           -9999             -9999  460.200780   167.328816    53.379310   \n",
       "539           -9999             -9999  349.181391   215.275641    58.379310   \n",
       "\n",
       "     Setpoint  SupplyTemp  InsideTemp      SolRad  SimulatedTemp  \n",
       "0        23.5        24.5   24.300000   61.321333      23.639075  \n",
       "1        23.5        15.5   24.283333   57.926100      23.243140  \n",
       "2        23.5        15.2   24.083333   54.902033      23.335477  \n",
       "3        23.5        14.9   23.933333   73.860700      23.524368  \n",
       "4        23.5        18.2   23.666667   76.042533      23.793051  \n",
       "..        ...         ...         ...         ...            ...  \n",
       "535      24.5        16.4   22.300000  361.247267      24.062549  \n",
       "536      24.5        17.6   22.300000  596.456167      24.158706  \n",
       "537      24.5        18.5   22.316667  550.335400      24.269707  \n",
       "538      24.5        20.0   22.450000  627.393133      24.348123  \n",
       "539      24.5        23.3   22.700000  564.347267      24.393026  \n",
       "\n",
       "[540 rows x 25 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Selected the potentially useful columns: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.loc[:, ['timestamp', 'zenith', 'azimuth', 'dni', 'dhi', 'OutsideTemp', 'Power', 'InsideTemp', 'SolRad', 'SimulatedTemp']]\n",
    "df.rename(columns = {'timestamp': 'timestamp_int'}, inplace = True)\n",
    "df.loc[:, 'timestamp'] = df_data.index\n",
    "df.set_index('timestamp', drop = True, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>timestamp_int</th>\n",
       "      <th>zenith</th>\n",
       "      <th>azimuth</th>\n",
       "      <th>dni</th>\n",
       "      <th>dhi</th>\n",
       "      <th>OutsideTemp</th>\n",
       "      <th>Power</th>\n",
       "      <th>InsideTemp</th>\n",
       "      <th>SolRad</th>\n",
       "      <th>SimulatedTemp</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>timestamp</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:00:00+02:00</th>\n",
       "      <td>201706012000</td>\n",
       "      <td>78.691622</td>\n",
       "      <td>290.430819</td>\n",
       "      <td>7.251337</td>\n",
       "      <td>59.908644</td>\n",
       "      <td>22.0</td>\n",
       "      <td>4325.034483</td>\n",
       "      <td>24.300000</td>\n",
       "      <td>61.321333</td>\n",
       "      <td>23.639075</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:05:00+02:00</th>\n",
       "      <td>201706012005</td>\n",
       "      <td>79.489651</td>\n",
       "      <td>291.279501</td>\n",
       "      <td>7.672114</td>\n",
       "      <td>56.537088</td>\n",
       "      <td>22.0</td>\n",
       "      <td>4287.000000</td>\n",
       "      <td>24.283333</td>\n",
       "      <td>57.926100</td>\n",
       "      <td>23.243140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:10:00+02:00</th>\n",
       "      <td>201706012010</td>\n",
       "      <td>80.282334</td>\n",
       "      <td>292.130503</td>\n",
       "      <td>8.423139</td>\n",
       "      <td>53.492674</td>\n",
       "      <td>22.0</td>\n",
       "      <td>4319.766667</td>\n",
       "      <td>24.083333</td>\n",
       "      <td>54.902033</td>\n",
       "      <td>23.335477</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:15:00+02:00</th>\n",
       "      <td>201706012015</td>\n",
       "      <td>81.069332</td>\n",
       "      <td>292.984123</td>\n",
       "      <td>52.657244</td>\n",
       "      <td>65.770239</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2893.344828</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>73.860700</td>\n",
       "      <td>23.524368</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:20:00+02:00</th>\n",
       "      <td>201706012020</td>\n",
       "      <td>81.850261</td>\n",
       "      <td>293.840653</td>\n",
       "      <td>94.364403</td>\n",
       "      <td>62.829177</td>\n",
       "      <td>22.0</td>\n",
       "      <td>59.137931</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>76.042533</td>\n",
       "      <td>23.793051</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:35:00+02:00</th>\n",
       "      <td>201706031635</td>\n",
       "      <td>43.923091</td>\n",
       "      <td>252.722275</td>\n",
       "      <td>64.970386</td>\n",
       "      <td>314.462614</td>\n",
       "      <td>24.0</td>\n",
       "      <td>62.137931</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>361.247267</td>\n",
       "      <td>24.062549</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:40:00+02:00</th>\n",
       "      <td>201706031640</td>\n",
       "      <td>44.746130</td>\n",
       "      <td>253.882437</td>\n",
       "      <td>530.910153</td>\n",
       "      <td>219.485890</td>\n",
       "      <td>24.0</td>\n",
       "      <td>57.482759</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>596.456167</td>\n",
       "      <td>24.158706</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:45:00+02:00</th>\n",
       "      <td>201706031645</td>\n",
       "      <td>45.573942</td>\n",
       "      <td>255.018953</td>\n",
       "      <td>428.243363</td>\n",
       "      <td>250.653973</td>\n",
       "      <td>24.0</td>\n",
       "      <td>56.233333</td>\n",
       "      <td>22.316667</td>\n",
       "      <td>550.335400</td>\n",
       "      <td>24.269707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:50:00+02:00</th>\n",
       "      <td>201706031650</td>\n",
       "      <td>46.406107</td>\n",
       "      <td>256.133161</td>\n",
       "      <td>667.400308</td>\n",
       "      <td>167.328816</td>\n",
       "      <td>24.0</td>\n",
       "      <td>53.379310</td>\n",
       "      <td>22.450000</td>\n",
       "      <td>627.393133</td>\n",
       "      <td>24.348123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:55:00+02:00</th>\n",
       "      <td>201706031655</td>\n",
       "      <td>47.242228</td>\n",
       "      <td>257.226338</td>\n",
       "      <td>514.333795</td>\n",
       "      <td>215.275641</td>\n",
       "      <td>24.0</td>\n",
       "      <td>58.379310</td>\n",
       "      <td>22.700000</td>\n",
       "      <td>564.347267</td>\n",
       "      <td>24.393026</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>540 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                           timestamp_int     zenith     azimuth         dni  \\\n",
       "timestamp                                                                     \n",
       "2017-06-01 20:00:00+02:00   201706012000  78.691622  290.430819    7.251337   \n",
       "2017-06-01 20:05:00+02:00   201706012005  79.489651  291.279501    7.672114   \n",
       "2017-06-01 20:10:00+02:00   201706012010  80.282334  292.130503    8.423139   \n",
       "2017-06-01 20:15:00+02:00   201706012015  81.069332  292.984123   52.657244   \n",
       "2017-06-01 20:20:00+02:00   201706012020  81.850261  293.840653   94.364403   \n",
       "...                                  ...        ...         ...         ...   \n",
       "2017-06-03 16:35:00+02:00   201706031635  43.923091  252.722275   64.970386   \n",
       "2017-06-03 16:40:00+02:00   201706031640  44.746130  253.882437  530.910153   \n",
       "2017-06-03 16:45:00+02:00   201706031645  45.573942  255.018953  428.243363   \n",
       "2017-06-03 16:50:00+02:00   201706031650  46.406107  256.133161  667.400308   \n",
       "2017-06-03 16:55:00+02:00   201706031655  47.242228  257.226338  514.333795   \n",
       "\n",
       "                                  dhi  OutsideTemp        Power  InsideTemp  \\\n",
       "timestamp                                                                     \n",
       "2017-06-01 20:00:00+02:00   59.908644         22.0  4325.034483   24.300000   \n",
       "2017-06-01 20:05:00+02:00   56.537088         22.0  4287.000000   24.283333   \n",
       "2017-06-01 20:10:00+02:00   53.492674         22.0  4319.766667   24.083333   \n",
       "2017-06-01 20:15:00+02:00   65.770239         22.0  2893.344828   23.933333   \n",
       "2017-06-01 20:20:00+02:00   62.829177         22.0    59.137931   23.666667   \n",
       "...                               ...          ...          ...         ...   \n",
       "2017-06-03 16:35:00+02:00  314.462614         24.0    62.137931   22.300000   \n",
       "2017-06-03 16:40:00+02:00  219.485890         24.0    57.482759   22.300000   \n",
       "2017-06-03 16:45:00+02:00  250.653973         24.0    56.233333   22.316667   \n",
       "2017-06-03 16:50:00+02:00  167.328816         24.0    53.379310   22.450000   \n",
       "2017-06-03 16:55:00+02:00  215.275641         24.0    58.379310   22.700000   \n",
       "\n",
       "                               SolRad  SimulatedTemp  \n",
       "timestamp                                             \n",
       "2017-06-01 20:00:00+02:00   61.321333      23.639075  \n",
       "2017-06-01 20:05:00+02:00   57.926100      23.243140  \n",
       "2017-06-01 20:10:00+02:00   54.902033      23.335477  \n",
       "2017-06-01 20:15:00+02:00   73.860700      23.524368  \n",
       "2017-06-01 20:20:00+02:00   76.042533      23.793051  \n",
       "...                               ...            ...  \n",
       "2017-06-03 16:35:00+02:00  361.247267      24.062549  \n",
       "2017-06-03 16:40:00+02:00  596.456167      24.158706  \n",
       "2017-06-03 16:45:00+02:00  550.335400      24.269707  \n",
       "2017-06-03 16:50:00+02:00  627.393133      24.348123  \n",
       "2017-06-03 16:55:00+02:00  564.347267      24.393026  \n",
       "\n",
       "[540 rows x 10 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Autoregressive inputs/outputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>timestamp_int</th>\n",
       "      <th>zenith</th>\n",
       "      <th>azimuth</th>\n",
       "      <th>dni</th>\n",
       "      <th>dhi</th>\n",
       "      <th>OutsideTemp</th>\n",
       "      <th>u</th>\n",
       "      <th>y</th>\n",
       "      <th>SolRad</th>\n",
       "      <th>SimulatedTemp</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>timestamp</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:00:00+02:00</th>\n",
       "      <td>201706012000</td>\n",
       "      <td>78.691622</td>\n",
       "      <td>290.430819</td>\n",
       "      <td>7.251337</td>\n",
       "      <td>59.908644</td>\n",
       "      <td>22.0</td>\n",
       "      <td>4325.034483</td>\n",
       "      <td>24.300000</td>\n",
       "      <td>61.321333</td>\n",
       "      <td>23.639075</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:05:00+02:00</th>\n",
       "      <td>201706012005</td>\n",
       "      <td>79.489651</td>\n",
       "      <td>291.279501</td>\n",
       "      <td>7.672114</td>\n",
       "      <td>56.537088</td>\n",
       "      <td>22.0</td>\n",
       "      <td>4287.000000</td>\n",
       "      <td>24.283333</td>\n",
       "      <td>57.926100</td>\n",
       "      <td>23.243140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:10:00+02:00</th>\n",
       "      <td>201706012010</td>\n",
       "      <td>80.282334</td>\n",
       "      <td>292.130503</td>\n",
       "      <td>8.423139</td>\n",
       "      <td>53.492674</td>\n",
       "      <td>22.0</td>\n",
       "      <td>4319.766667</td>\n",
       "      <td>24.083333</td>\n",
       "      <td>54.902033</td>\n",
       "      <td>23.335477</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:15:00+02:00</th>\n",
       "      <td>201706012015</td>\n",
       "      <td>81.069332</td>\n",
       "      <td>292.984123</td>\n",
       "      <td>52.657244</td>\n",
       "      <td>65.770239</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2893.344828</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>73.860700</td>\n",
       "      <td>23.524368</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:20:00+02:00</th>\n",
       "      <td>201706012020</td>\n",
       "      <td>81.850261</td>\n",
       "      <td>293.840653</td>\n",
       "      <td>94.364403</td>\n",
       "      <td>62.829177</td>\n",
       "      <td>22.0</td>\n",
       "      <td>59.137931</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>76.042533</td>\n",
       "      <td>23.793051</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:35:00+02:00</th>\n",
       "      <td>201706031635</td>\n",
       "      <td>43.923091</td>\n",
       "      <td>252.722275</td>\n",
       "      <td>64.970386</td>\n",
       "      <td>314.462614</td>\n",
       "      <td>24.0</td>\n",
       "      <td>62.137931</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>361.247267</td>\n",
       "      <td>24.062549</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:40:00+02:00</th>\n",
       "      <td>201706031640</td>\n",
       "      <td>44.746130</td>\n",
       "      <td>253.882437</td>\n",
       "      <td>530.910153</td>\n",
       "      <td>219.485890</td>\n",
       "      <td>24.0</td>\n",
       "      <td>57.482759</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>596.456167</td>\n",
       "      <td>24.158706</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:45:00+02:00</th>\n",
       "      <td>201706031645</td>\n",
       "      <td>45.573942</td>\n",
       "      <td>255.018953</td>\n",
       "      <td>428.243363</td>\n",
       "      <td>250.653973</td>\n",
       "      <td>24.0</td>\n",
       "      <td>56.233333</td>\n",
       "      <td>22.316667</td>\n",
       "      <td>550.335400</td>\n",
       "      <td>24.269707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:50:00+02:00</th>\n",
       "      <td>201706031650</td>\n",
       "      <td>46.406107</td>\n",
       "      <td>256.133161</td>\n",
       "      <td>667.400308</td>\n",
       "      <td>167.328816</td>\n",
       "      <td>24.0</td>\n",
       "      <td>53.379310</td>\n",
       "      <td>22.450000</td>\n",
       "      <td>627.393133</td>\n",
       "      <td>24.348123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:55:00+02:00</th>\n",
       "      <td>201706031655</td>\n",
       "      <td>47.242228</td>\n",
       "      <td>257.226338</td>\n",
       "      <td>514.333795</td>\n",
       "      <td>215.275641</td>\n",
       "      <td>24.0</td>\n",
       "      <td>58.379310</td>\n",
       "      <td>22.700000</td>\n",
       "      <td>564.347267</td>\n",
       "      <td>24.393026</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>540 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                           timestamp_int     zenith     azimuth         dni  \\\n",
       "timestamp                                                                     \n",
       "2017-06-01 20:00:00+02:00   201706012000  78.691622  290.430819    7.251337   \n",
       "2017-06-01 20:05:00+02:00   201706012005  79.489651  291.279501    7.672114   \n",
       "2017-06-01 20:10:00+02:00   201706012010  80.282334  292.130503    8.423139   \n",
       "2017-06-01 20:15:00+02:00   201706012015  81.069332  292.984123   52.657244   \n",
       "2017-06-01 20:20:00+02:00   201706012020  81.850261  293.840653   94.364403   \n",
       "...                                  ...        ...         ...         ...   \n",
       "2017-06-03 16:35:00+02:00   201706031635  43.923091  252.722275   64.970386   \n",
       "2017-06-03 16:40:00+02:00   201706031640  44.746130  253.882437  530.910153   \n",
       "2017-06-03 16:45:00+02:00   201706031645  45.573942  255.018953  428.243363   \n",
       "2017-06-03 16:50:00+02:00   201706031650  46.406107  256.133161  667.400308   \n",
       "2017-06-03 16:55:00+02:00   201706031655  47.242228  257.226338  514.333795   \n",
       "\n",
       "                                  dhi  OutsideTemp            u          y  \\\n",
       "timestamp                                                                    \n",
       "2017-06-01 20:00:00+02:00   59.908644         22.0  4325.034483  24.300000   \n",
       "2017-06-01 20:05:00+02:00   56.537088         22.0  4287.000000  24.283333   \n",
       "2017-06-01 20:10:00+02:00   53.492674         22.0  4319.766667  24.083333   \n",
       "2017-06-01 20:15:00+02:00   65.770239         22.0  2893.344828  23.933333   \n",
       "2017-06-01 20:20:00+02:00   62.829177         22.0    59.137931  23.666667   \n",
       "...                               ...          ...          ...        ...   \n",
       "2017-06-03 16:35:00+02:00  314.462614         24.0    62.137931  22.300000   \n",
       "2017-06-03 16:40:00+02:00  219.485890         24.0    57.482759  22.300000   \n",
       "2017-06-03 16:45:00+02:00  250.653973         24.0    56.233333  22.316667   \n",
       "2017-06-03 16:50:00+02:00  167.328816         24.0    53.379310  22.450000   \n",
       "2017-06-03 16:55:00+02:00  215.275641         24.0    58.379310  22.700000   \n",
       "\n",
       "                               SolRad  SimulatedTemp  \n",
       "timestamp                                             \n",
       "2017-06-01 20:00:00+02:00   61.321333      23.639075  \n",
       "2017-06-01 20:05:00+02:00   57.926100      23.243140  \n",
       "2017-06-01 20:10:00+02:00   54.902033      23.335477  \n",
       "2017-06-01 20:15:00+02:00   73.860700      23.524368  \n",
       "2017-06-01 20:20:00+02:00   76.042533      23.793051  \n",
       "...                               ...            ...  \n",
       "2017-06-03 16:35:00+02:00  361.247267      24.062549  \n",
       "2017-06-03 16:40:00+02:00  596.456167      24.158706  \n",
       "2017-06-03 16:45:00+02:00  550.335400      24.269707  \n",
       "2017-06-03 16:50:00+02:00  627.393133      24.348123  \n",
       "2017-06-03 16:55:00+02:00  564.347267      24.393026  \n",
       "\n",
       "[540 rows x 10 columns]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.rename(columns = {'Power': 'u', 'InsideTemp': 'y'}, inplace = True)\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Add input lags:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "lu = 1\n",
    "\n",
    "for idx in range(1, lu + 1):\n",
    "    df[f\"u_{idx}\"] = df['u'].shift(idx)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Add output lags:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "ly = 3\n",
    "\n",
    "for idx in range(1, ly + 1):\n",
    "    df[f\"y_{idx}\"] = df['y'].shift(idx)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.dropna(inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>timestamp_int</th>\n",
       "      <th>zenith</th>\n",
       "      <th>azimuth</th>\n",
       "      <th>dni</th>\n",
       "      <th>dhi</th>\n",
       "      <th>OutsideTemp</th>\n",
       "      <th>u</th>\n",
       "      <th>y</th>\n",
       "      <th>SolRad</th>\n",
       "      <th>SimulatedTemp</th>\n",
       "      <th>u_1</th>\n",
       "      <th>y_1</th>\n",
       "      <th>y_2</th>\n",
       "      <th>y_3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>timestamp</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:15:00+02:00</th>\n",
       "      <td>201706012015</td>\n",
       "      <td>81.069332</td>\n",
       "      <td>292.984123</td>\n",
       "      <td>52.657244</td>\n",
       "      <td>65.770239</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2893.344828</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>73.860700</td>\n",
       "      <td>23.524368</td>\n",
       "      <td>4319.766667</td>\n",
       "      <td>24.083333</td>\n",
       "      <td>24.283333</td>\n",
       "      <td>24.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:20:00+02:00</th>\n",
       "      <td>201706012020</td>\n",
       "      <td>81.850261</td>\n",
       "      <td>293.840653</td>\n",
       "      <td>94.364403</td>\n",
       "      <td>62.829177</td>\n",
       "      <td>22.0</td>\n",
       "      <td>59.137931</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>76.042533</td>\n",
       "      <td>23.793051</td>\n",
       "      <td>2893.344828</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>24.083333</td>\n",
       "      <td>24.283333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:25:00+02:00</th>\n",
       "      <td>201706012025</td>\n",
       "      <td>82.624676</td>\n",
       "      <td>294.700379</td>\n",
       "      <td>72.713713</td>\n",
       "      <td>55.785907</td>\n",
       "      <td>22.0</td>\n",
       "      <td>58.241379</td>\n",
       "      <td>23.650000</td>\n",
       "      <td>64.981967</td>\n",
       "      <td>23.690749</td>\n",
       "      <td>59.137931</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>24.083333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:30:00+02:00</th>\n",
       "      <td>201706012030</td>\n",
       "      <td>83.392049</td>\n",
       "      <td>295.563581</td>\n",
       "      <td>24.601803</td>\n",
       "      <td>43.887954</td>\n",
       "      <td>22.0</td>\n",
       "      <td>59.000000</td>\n",
       "      <td>23.633333</td>\n",
       "      <td>46.667567</td>\n",
       "      <td>23.616543</td>\n",
       "      <td>58.241379</td>\n",
       "      <td>23.650000</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>23.933333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:35:00+02:00</th>\n",
       "      <td>201706012035</td>\n",
       "      <td>84.151733</td>\n",
       "      <td>296.430536</td>\n",
       "      <td>11.237512</td>\n",
       "      <td>33.883988</td>\n",
       "      <td>22.0</td>\n",
       "      <td>61.103448</td>\n",
       "      <td>23.800000</td>\n",
       "      <td>35.002967</td>\n",
       "      <td>23.566295</td>\n",
       "      <td>59.000000</td>\n",
       "      <td>23.633333</td>\n",
       "      <td>23.650000</td>\n",
       "      <td>23.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:35:00+02:00</th>\n",
       "      <td>201706031635</td>\n",
       "      <td>43.923091</td>\n",
       "      <td>252.722275</td>\n",
       "      <td>64.970386</td>\n",
       "      <td>314.462614</td>\n",
       "      <td>24.0</td>\n",
       "      <td>62.137931</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>361.247267</td>\n",
       "      <td>24.062549</td>\n",
       "      <td>4348.068966</td>\n",
       "      <td>22.500000</td>\n",
       "      <td>22.683333</td>\n",
       "      <td>22.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:40:00+02:00</th>\n",
       "      <td>201706031640</td>\n",
       "      <td>44.746130</td>\n",
       "      <td>253.882437</td>\n",
       "      <td>530.910153</td>\n",
       "      <td>219.485890</td>\n",
       "      <td>24.0</td>\n",
       "      <td>57.482759</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>596.456167</td>\n",
       "      <td>24.158706</td>\n",
       "      <td>62.137931</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>22.500000</td>\n",
       "      <td>22.683333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:45:00+02:00</th>\n",
       "      <td>201706031645</td>\n",
       "      <td>45.573942</td>\n",
       "      <td>255.018953</td>\n",
       "      <td>428.243363</td>\n",
       "      <td>250.653973</td>\n",
       "      <td>24.0</td>\n",
       "      <td>56.233333</td>\n",
       "      <td>22.316667</td>\n",
       "      <td>550.335400</td>\n",
       "      <td>24.269707</td>\n",
       "      <td>57.482759</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>22.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:50:00+02:00</th>\n",
       "      <td>201706031650</td>\n",
       "      <td>46.406107</td>\n",
       "      <td>256.133161</td>\n",
       "      <td>667.400308</td>\n",
       "      <td>167.328816</td>\n",
       "      <td>24.0</td>\n",
       "      <td>53.379310</td>\n",
       "      <td>22.450000</td>\n",
       "      <td>627.393133</td>\n",
       "      <td>24.348123</td>\n",
       "      <td>56.233333</td>\n",
       "      <td>22.316667</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>22.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-03 16:55:00+02:00</th>\n",
       "      <td>201706031655</td>\n",
       "      <td>47.242228</td>\n",
       "      <td>257.226338</td>\n",
       "      <td>514.333795</td>\n",
       "      <td>215.275641</td>\n",
       "      <td>24.0</td>\n",
       "      <td>58.379310</td>\n",
       "      <td>22.700000</td>\n",
       "      <td>564.347267</td>\n",
       "      <td>24.393026</td>\n",
       "      <td>53.379310</td>\n",
       "      <td>22.450000</td>\n",
       "      <td>22.316667</td>\n",
       "      <td>22.300000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>537 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                           timestamp_int     zenith     azimuth         dni  \\\n",
       "timestamp                                                                     \n",
       "2017-06-01 20:15:00+02:00   201706012015  81.069332  292.984123   52.657244   \n",
       "2017-06-01 20:20:00+02:00   201706012020  81.850261  293.840653   94.364403   \n",
       "2017-06-01 20:25:00+02:00   201706012025  82.624676  294.700379   72.713713   \n",
       "2017-06-01 20:30:00+02:00   201706012030  83.392049  295.563581   24.601803   \n",
       "2017-06-01 20:35:00+02:00   201706012035  84.151733  296.430536   11.237512   \n",
       "...                                  ...        ...         ...         ...   \n",
       "2017-06-03 16:35:00+02:00   201706031635  43.923091  252.722275   64.970386   \n",
       "2017-06-03 16:40:00+02:00   201706031640  44.746130  253.882437  530.910153   \n",
       "2017-06-03 16:45:00+02:00   201706031645  45.573942  255.018953  428.243363   \n",
       "2017-06-03 16:50:00+02:00   201706031650  46.406107  256.133161  667.400308   \n",
       "2017-06-03 16:55:00+02:00   201706031655  47.242228  257.226338  514.333795   \n",
       "\n",
       "                                  dhi  OutsideTemp            u          y  \\\n",
       "timestamp                                                                    \n",
       "2017-06-01 20:15:00+02:00   65.770239         22.0  2893.344828  23.933333   \n",
       "2017-06-01 20:20:00+02:00   62.829177         22.0    59.137931  23.666667   \n",
       "2017-06-01 20:25:00+02:00   55.785907         22.0    58.241379  23.650000   \n",
       "2017-06-01 20:30:00+02:00   43.887954         22.0    59.000000  23.633333   \n",
       "2017-06-01 20:35:00+02:00   33.883988         22.0    61.103448  23.800000   \n",
       "...                               ...          ...          ...        ...   \n",
       "2017-06-03 16:35:00+02:00  314.462614         24.0    62.137931  22.300000   \n",
       "2017-06-03 16:40:00+02:00  219.485890         24.0    57.482759  22.300000   \n",
       "2017-06-03 16:45:00+02:00  250.653973         24.0    56.233333  22.316667   \n",
       "2017-06-03 16:50:00+02:00  167.328816         24.0    53.379310  22.450000   \n",
       "2017-06-03 16:55:00+02:00  215.275641         24.0    58.379310  22.700000   \n",
       "\n",
       "                               SolRad  SimulatedTemp          u_1        y_1  \\\n",
       "timestamp                                                                      \n",
       "2017-06-01 20:15:00+02:00   73.860700      23.524368  4319.766667  24.083333   \n",
       "2017-06-01 20:20:00+02:00   76.042533      23.793051  2893.344828  23.933333   \n",
       "2017-06-01 20:25:00+02:00   64.981967      23.690749    59.137931  23.666667   \n",
       "2017-06-01 20:30:00+02:00   46.667567      23.616543    58.241379  23.650000   \n",
       "2017-06-01 20:35:00+02:00   35.002967      23.566295    59.000000  23.633333   \n",
       "...                               ...            ...          ...        ...   \n",
       "2017-06-03 16:35:00+02:00  361.247267      24.062549  4348.068966  22.500000   \n",
       "2017-06-03 16:40:00+02:00  596.456167      24.158706    62.137931  22.300000   \n",
       "2017-06-03 16:45:00+02:00  550.335400      24.269707    57.482759  22.300000   \n",
       "2017-06-03 16:50:00+02:00  627.393133      24.348123    56.233333  22.316667   \n",
       "2017-06-03 16:55:00+02:00  564.347267      24.393026    53.379310  22.450000   \n",
       "\n",
       "                                 y_2        y_3  \n",
       "timestamp                                        \n",
       "2017-06-01 20:15:00+02:00  24.283333  24.300000  \n",
       "2017-06-01 20:20:00+02:00  24.083333  24.283333  \n",
       "2017-06-01 20:25:00+02:00  23.933333  24.083333  \n",
       "2017-06-01 20:30:00+02:00  23.666667  23.933333  \n",
       "2017-06-01 20:35:00+02:00  23.650000  23.666667  \n",
       "...                              ...        ...  \n",
       "2017-06-03 16:35:00+02:00  22.683333  22.900000  \n",
       "2017-06-03 16:40:00+02:00  22.500000  22.683333  \n",
       "2017-06-03 16:45:00+02:00  22.300000  22.500000  \n",
       "2017-06-03 16:50:00+02:00  22.300000  22.300000  \n",
       "2017-06-03 16:55:00+02:00  22.316667  22.300000  \n",
       "\n",
       "[537 rows x 14 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Formalize everything into a function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_autoregressive_df(exp_id, lu = 1, ly = 3):\n",
    "    \n",
    "    df_wdb = pd.read_pickle(f\"../Data/Experimental_python/Exp{exp_id}_WDB.pkl\")\n",
    "    \n",
    "    df_carnot = pd.read_pickle(f\"../Data/CARNOT_output/Exp{exp_id}_full.pkl\")\n",
    "    df_data = df_carnot.loc[:, ['Power', 'Heat', 'Setpoint', 'OutsideTemp', 'SupplyTemp', 'InsideTemp', 'SolRad']]\n",
    "    df_simulated = df_carnot.loc[:, 'SimulatedTemp']\n",
    "\n",
    "    df = pd.concat([df_wdb, df_data.reset_index(), df_simulated.reset_index()], axis = 1)\n",
    "\n",
    "    df = df.loc[:,~df.columns.duplicated()]\n",
    "    \n",
    "    # Select the potentially useful columns\n",
    "    #df = df.loc[:, ['timestamp', 'zenith', 'azimuth', 'dni', 'dhi', 'OutsideTemp', 'Power', 'InsideTemp', 'SolRad', 'Setpoint']]\n",
    "    df = df.loc[:, ['timestamp','SolRad', 'OutsideTemp', 'Heat', 'InsideTemp']]\n",
    "\n",
    "    df.drop(columns = ['timestamp'], inplace = True)\n",
    "    df.loc[:, 'timestamp'] = df_data.index\n",
    "    df.set_index('timestamp', drop = True, inplace = True)\n",
    "    \n",
    "    # Select the input/output and drop the columns that doesn't make to be used\n",
    "    dyn_in = 'Heat'\n",
    "    dyn_out = 'InsideTemp'    \n",
    "    df.rename(columns = {dyn_in: 'u', dyn_out: 'y'}, inplace = True)\n",
    "\n",
    "    # Add the regressive inputs/outputs\n",
    "    for idx in range(1, lu + 1):\n",
    "        df[f\"u_{idx}\"] = df['u'].shift(idx)\n",
    "        \n",
    "    for idx in range(1, ly + 1):\n",
    "        df[f\"y_{idx}\"] = df['y'].shift(idx)\n",
    "        \n",
    "    # Since some lines now have holes, drop them\n",
    "    df.dropna(inplace = True)\n",
    "    \n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SolRad</th>\n",
       "      <th>OutsideTemp</th>\n",
       "      <th>u</th>\n",
       "      <th>y</th>\n",
       "      <th>u_1</th>\n",
       "      <th>y_1</th>\n",
       "      <th>y_2</th>\n",
       "      <th>y_3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>timestamp</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:15:00+02:00</th>\n",
       "      <td>73.860700</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-8680.034483</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>-12959.300000</td>\n",
       "      <td>24.083333</td>\n",
       "      <td>24.283333</td>\n",
       "      <td>24.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:20:00+02:00</th>\n",
       "      <td>76.042533</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-177.413793</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>-8680.034483</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>24.083333</td>\n",
       "      <td>24.283333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:25:00+02:00</th>\n",
       "      <td>64.981967</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-174.724138</td>\n",
       "      <td>23.650000</td>\n",
       "      <td>-177.413793</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>23.933333</td>\n",
       "      <td>24.083333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:30:00+02:00</th>\n",
       "      <td>46.667567</td>\n",
       "      <td>22.0</td>\n",
       "      <td>59.000000</td>\n",
       "      <td>23.633333</td>\n",
       "      <td>-174.724138</td>\n",
       "      <td>23.650000</td>\n",
       "      <td>23.666667</td>\n",
       "      <td>23.933333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-01 20:35:00+02:00</th>\n",
       "      <td>35.002967</td>\n",
       "      <td>22.0</td>\n",
       "      <td>61.103448</td>\n",
       "      <td>23.800000</td>\n",
       "      <td>59.000000</td>\n",
       "      <td>23.633333</td>\n",
       "      <td>23.650000</td>\n",
       "      <td>23.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-20 05:35:00+02:00</th>\n",
       "      <td>3.260000</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-28.551724</td>\n",
       "      <td>22.766667</td>\n",
       "      <td>-27.931034</td>\n",
       "      <td>22.750000</td>\n",
       "      <td>22.733333</td>\n",
       "      <td>22.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-20 05:40:00+02:00</th>\n",
       "      <td>3.250000</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-17.000000</td>\n",
       "      <td>22.733333</td>\n",
       "      <td>-28.551724</td>\n",
       "      <td>22.766667</td>\n",
       "      <td>22.750000</td>\n",
       "      <td>22.733333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-20 05:45:00+02:00</th>\n",
       "      <td>3.240000</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-27.413793</td>\n",
       "      <td>22.750000</td>\n",
       "      <td>-17.000000</td>\n",
       "      <td>22.733333</td>\n",
       "      <td>22.766667</td>\n",
       "      <td>22.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-20 05:50:00+02:00</th>\n",
       "      <td>3.340000</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-12.620690</td>\n",
       "      <td>22.733333</td>\n",
       "      <td>-27.413793</td>\n",
       "      <td>22.750000</td>\n",
       "      <td>22.733333</td>\n",
       "      <td>22.766667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-20 05:55:00+02:00</th>\n",
       "      <td>3.380000</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-12.700000</td>\n",
       "      <td>22.800000</td>\n",
       "      <td>-12.620690</td>\n",
       "      <td>22.733333</td>\n",
       "      <td>22.750000</td>\n",
       "      <td>22.733333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4221 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                              SolRad  OutsideTemp            u          y  \\\n",
       "timestamp                                                                   \n",
       "2017-06-01 20:15:00+02:00  73.860700         22.0 -8680.034483  23.933333   \n",
       "2017-06-01 20:20:00+02:00  76.042533         22.0  -177.413793  23.666667   \n",
       "2017-06-01 20:25:00+02:00  64.981967         22.0  -174.724138  23.650000   \n",
       "2017-06-01 20:30:00+02:00  46.667567         22.0    59.000000  23.633333   \n",
       "2017-06-01 20:35:00+02:00  35.002967         22.0    61.103448  23.800000   \n",
       "...                              ...          ...          ...        ...   \n",
       "2017-07-20 05:35:00+02:00   3.260000         22.0   -28.551724  22.766667   \n",
       "2017-07-20 05:40:00+02:00   3.250000         22.0   -17.000000  22.733333   \n",
       "2017-07-20 05:45:00+02:00   3.240000         22.0   -27.413793  22.750000   \n",
       "2017-07-20 05:50:00+02:00   3.340000         22.0   -12.620690  22.733333   \n",
       "2017-07-20 05:55:00+02:00   3.380000         22.0   -12.700000  22.800000   \n",
       "\n",
       "                                    u_1        y_1        y_2        y_3  \n",
       "timestamp                                                                 \n",
       "2017-06-01 20:15:00+02:00 -12959.300000  24.083333  24.283333  24.300000  \n",
       "2017-06-01 20:20:00+02:00  -8680.034483  23.933333  24.083333  24.283333  \n",
       "2017-06-01 20:25:00+02:00   -177.413793  23.666667  23.933333  24.083333  \n",
       "2017-06-01 20:30:00+02:00   -174.724138  23.650000  23.666667  23.933333  \n",
       "2017-06-01 20:35:00+02:00     59.000000  23.633333  23.650000  23.666667  \n",
       "...                                 ...        ...        ...        ...  \n",
       "2017-07-20 05:35:00+02:00    -27.931034  22.750000  22.733333  22.750000  \n",
       "2017-07-20 05:40:00+02:00    -28.551724  22.766667  22.750000  22.733333  \n",
       "2017-07-20 05:45:00+02:00    -17.000000  22.733333  22.766667  22.750000  \n",
       "2017-07-20 05:50:00+02:00    -27.413793  22.750000  22.733333  22.766667  \n",
       "2017-07-20 05:55:00+02:00    -12.620690  22.733333  22.750000  22.733333  \n",
       "\n",
       "[4221 rows x 8 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#lu = 1, ly = 3 defined in a preceding cell\n",
    "df_compiled = load_autoregressive_df(1, lu = lu, ly = ly)\n",
    "for idx in [2,4,6,7]:\n",
    "    df_compiled = df_compiled.append(load_autoregressive_df(idx, lu = lu, ly = ly))\n",
    "df_compiled"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Gaussian Process fitting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import RobustScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_scaler = RobustScaler()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sample the training data from the whole dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_sampled = df_compiled.sample(n = 150)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Save the dataset since it's needed when loading the model from saved files:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_sampled.to_pickle(\"gp_trainset.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_input = df_sampled.drop(columns = ['y'])\n",
    "df_output = df_sampled['y']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "np_input = df_input.to_numpy()\n",
    "np_output = df_output.to_numpy().reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Scale the data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "np_input_sc = x_scaler.fit_transform(np_input)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th>name                       </th><th>class    </th><th>transform  </th><th>prior  </th><th>trainable  </th><th>shape  </th><th>dtype  </th><th>value         </th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td>Sum.kernels[0].variance    </td><td>Parameter</td><td>Softplus   </td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>1.0           </td></tr>\n",
       "<tr><td>Sum.kernels[0].lengthscales</td><td>Parameter</td><td>Softplus   </td><td>       </td><td>True       </td><td>(7,)   </td><td>float64</td><td>[1., 1., 1....</td></tr>\n",
       "<tr><td>Sum.kernels[1].variance    </td><td>Parameter</td><td>Softplus   </td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>1.0           </td></tr>\n",
       "</tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "k = gpflow.kernels.SquaredExponential(lengthscales=([1] * np_input.shape[1])) + gpflow.kernels.Constant() + gpflow.kernels.White()\n",
    "k = gpflow.kernels.SquaredExponential(lengthscales=([1] * np_input.shape[1])) + gpflow.kernels.Constant()\n",
    "print_summary(k)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th>name                              </th><th>class    </th><th>transform       </th><th>prior  </th><th>trainable  </th><th>shape  </th><th>dtype  </th><th>value         </th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td>GPR.kernel.kernels[0].variance    </td><td>Parameter</td><td>Softplus        </td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>1.0           </td></tr>\n",
       "<tr><td>GPR.kernel.kernels[0].lengthscales</td><td>Parameter</td><td>Softplus        </td><td>       </td><td>True       </td><td>(7,)   </td><td>float64</td><td>[1., 1., 1....</td></tr>\n",
       "<tr><td>GPR.kernel.kernels[1].variance    </td><td>Parameter</td><td>Softplus        </td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>1.0           </td></tr>\n",
       "<tr><td>GPR.likelihood.variance           </td><td>Parameter</td><td>Softplus + Shift</td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>1.0           </td></tr>\n",
       "</tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "m = gpflow.models.GPR(\n",
    "    data = (np_input_sc, np_output), \n",
    "    kernel = k, \n",
    "    mean_function = None\n",
    "    )\n",
    "print_summary(m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [],
   "source": [
    "opt = gpflow.optimizers.Scipy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datetime import datetime"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finished fitting in 0:00:01.800025\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th>name                              </th><th>class    </th><th>transform       </th><th>prior  </th><th>trainable  </th><th>shape  </th><th>dtype  </th><th>value                                       </th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td>GPR.kernel.kernels[0].variance    </td><td>Parameter</td><td>Softplus        </td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>522.3146176324312                           </td></tr>\n",
       "<tr><td>GPR.kernel.kernels[0].lengthscales</td><td>Parameter</td><td>Softplus        </td><td>       </td><td>True       </td><td>(7,)   </td><td>float64</td><td>[398.28296795, 262.16471714, 1574.2697205...</td></tr>\n",
       "<tr><td>GPR.kernel.kernels[1].variance    </td><td>Parameter</td><td>Softplus        </td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>600.9888765600585                           </td></tr>\n",
       "<tr><td>GPR.likelihood.variance           </td><td>Parameter</td><td>Softplus + Shift</td><td>       </td><td>True       </td><td>()     </td><td>float64</td><td>0.005945197285215412                        </td></tr>\n",
       "</tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "start_time = datetime.now()\n",
    "opt.minimize(m.training_loss, m.trainable_variables)\n",
    "print(f\"Finished fitting in {datetime.now() - start_time}\")\n",
    "print_summary(m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_day = 5\n",
    "df_test = load_autoregressive_df(test_day, lu = lu, ly = ly)\n",
    "np_test_in = df_test.drop(columns = ['y']).to_numpy()\n",
    "np_test_in_sc = x_scaler.transform(np_test_in)\n",
    "np_test_out = df_test['y'].to_numpy().reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [],
   "source": [
    "mean, var = m.predict_f(np_test_in_sc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize = (20, 5))\n",
    "plt.plot(df_test.index, np_test_out[:, :], label = 'Measured data')\n",
    "plt.plot(df_test.index, mean[:, :], label = 'Gaussian Process Prediction')\n",
    "plt.fill_between(\n",
    "    df_test.index, \n",
    "    mean[:, 0] - 1.96 * np.sqrt(var[:, 0]),\n",
    "    mean[:, 0] + 1.96 * np.sqrt(var[:, 0]),\n",
    "    alpha = 0.2\n",
    ")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "## generate test points for prediction\n",
    "xx = x_scaler.transform(np_test_in)\n",
    "\n",
    "## predict mean and variance of latent GP at test points\n",
    "mean, var = m.predict_f(xx)\n",
    "\n",
    "## generate 10 samples from posterior\n",
    "tf.random.set_seed(1)  # for reproducibility\n",
    "samples = m.predict_f_samples(xx, 10)  # shape (10, 100, 1)\n",
    "\n",
    "## plot\n",
    "plt.figure(figsize=(20, 5))\n",
    "plt.title('Posterior sample functions')\n",
    "plt.plot(df_test.index, mean, \"C0\", lw=2)\n",
    "plt.fill_between(\n",
    "    df_test.index,\n",
    "    mean[:, 0] - 1.96 * np.sqrt(var[:, 0]),\n",
    "    mean[:, 0] + 1.96 * np.sqrt(var[:, 0]),\n",
    "    color=\"C0\",\n",
    "    alpha=0.2,\n",
    ")\n",
    "plt.plot(df_test.index, samples[:, :, 0].numpy().T, \"C0\", linewidth=0.5)\n",
    "#plt.plot(df_test.index, np_test_out[:, :], ':', color = 'darkorange', lw = 2)\n",
    "#_ = plt.ylim(21, 23.5)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [],
   "source": [
    "err = abs(np_test_out - mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0008520598721588613"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.max(var)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "plt.plot(df_test.index, 1.96 * np.sqrt(var), label = '1.96 * std')\n",
    "plt.plot(df_test.index, err, '.', label = 'Error')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "17\n"
     ]
    }
   ],
   "source": [
    "big_err = (err > 1.96*np.sqrt(var)).numpy().sum()\n",
    "print(big_err)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9754689754689755"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "1 - big_err/len(err)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Export the fitted model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "m_params = gpflow.utilities.parameter_dict(m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(m_params, open(Path(Path.cwd(), 'gp_params.gpf'), 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(x_scaler, open(Path(Path.cwd(), 'x_scaler.pkl'), 'wb'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Re-import the model and compare prediction with first model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "k_loaded = gpflow.kernels.SquaredExponential(lengthscales=([1] * np_input.shape[1])) + gpflow.kernels.Constant()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "m_loaded = gpflow.models.GPR(\n",
    "    data = (np_input_sc, np_output), \n",
    "    kernel = k_loaded,\n",
    "    mean_function = None\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "m_params_loaded = pickle.load(open(Path(Path.cwd(), 'gp_params.gpf'), 'rb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "gpflow.utilities.multiple_assign(m_loaded, m_params_loaded)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "mean_loaded, var_loaded = m_loaded.predict_f(np_test_in_sc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize = (20, 5))\n",
    "plt.plot(df_test.index, np_test_out[:, :], label = 'Measured data')\n",
    "plt.plot(df_test.index, mean[:, :], label = 'Gaussian Process Prediction orig')\n",
    "plt.plot(df_test.index, mean_loaded[:, :], label = 'Gaussian Process Prediction loaded')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "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>SolRad</th>\n",
       "      <th>OutsideTemp</th>\n",
       "      <th>u</th>\n",
       "      <th>y</th>\n",
       "      <th>u_1</th>\n",
       "      <th>y_1</th>\n",
       "      <th>y_2</th>\n",
       "      <th>y_3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>timestamp</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2017-07-19 15:05:00+02:00</th>\n",
       "      <td>680.640000</td>\n",
       "      <td>28.0</td>\n",
       "      <td>-14422.100000</td>\n",
       "      <td>22.583333</td>\n",
       "      <td>-14336.689655</td>\n",
       "      <td>22.600000</td>\n",
       "      <td>22.733333</td>\n",
       "      <td>22.783333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-22 02:25:00+02:00</th>\n",
       "      <td>3.403067</td>\n",
       "      <td>28.0</td>\n",
       "      <td>-62.586207</td>\n",
       "      <td>22.566667</td>\n",
       "      <td>-90.517241</td>\n",
       "      <td>22.600000</td>\n",
       "      <td>22.650000</td>\n",
       "      <td>22.833333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-16 13:45:00+02:00</th>\n",
       "      <td>885.935000</td>\n",
       "      <td>21.0</td>\n",
       "      <td>-12772.700000</td>\n",
       "      <td>22.716667</td>\n",
       "      <td>-13091.586207</td>\n",
       "      <td>22.866667</td>\n",
       "      <td>22.850000</td>\n",
       "      <td>22.633333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-15 03:50:00+02:00</th>\n",
       "      <td>3.090000</td>\n",
       "      <td>18.0</td>\n",
       "      <td>-13.233333</td>\n",
       "      <td>21.566667</td>\n",
       "      <td>-12.758621</td>\n",
       "      <td>21.516667</td>\n",
       "      <td>21.533333</td>\n",
       "      <td>21.558333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-18 07:05:00+02:00</th>\n",
       "      <td>91.620000</td>\n",
       "      <td>19.0</td>\n",
       "      <td>-5.793103</td>\n",
       "      <td>22.566667</td>\n",
       "      <td>6.517241</td>\n",
       "      <td>22.533333</td>\n",
       "      <td>22.566667</td>\n",
       "      <td>22.566667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-11 13:20:00+02:00</th>\n",
       "      <td>916.328067</td>\n",
       "      <td>22.5</td>\n",
       "      <td>2138.344828</td>\n",
       "      <td>23.100000</td>\n",
       "      <td>-15974.793103</td>\n",
       "      <td>23.200000</td>\n",
       "      <td>23.383333</td>\n",
       "      <td>23.583333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-19 16:05:00+02:00</th>\n",
       "      <td>450.750000</td>\n",
       "      <td>28.0</td>\n",
       "      <td>-14195.275862</td>\n",
       "      <td>22.833333</td>\n",
       "      <td>-14086.500000</td>\n",
       "      <td>23.000000</td>\n",
       "      <td>23.033333</td>\n",
       "      <td>23.166667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-15 20:30:00+02:00</th>\n",
       "      <td>95.620000</td>\n",
       "      <td>22.0</td>\n",
       "      <td>-6755.379310</td>\n",
       "      <td>23.066667</td>\n",
       "      <td>-2.793103</td>\n",
       "      <td>22.833333</td>\n",
       "      <td>22.833333</td>\n",
       "      <td>22.633333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-06-22 04:05:00+02:00</th>\n",
       "      <td>3.310567</td>\n",
       "      <td>23.0</td>\n",
       "      <td>-42.000000</td>\n",
       "      <td>22.691667</td>\n",
       "      <td>-65.600000</td>\n",
       "      <td>22.658333</td>\n",
       "      <td>22.583333</td>\n",
       "      <td>22.583333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017-07-15 11:30:00+02:00</th>\n",
       "      <td>801.415000</td>\n",
       "      <td>21.0</td>\n",
       "      <td>2374.068966</td>\n",
       "      <td>21.350000</td>\n",
       "      <td>-12525.620690</td>\n",
       "      <td>21.350000</td>\n",
       "      <td>21.216667</td>\n",
       "      <td>21.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                               SolRad  OutsideTemp             u          y  \\\n",
       "timestamp                                                                     \n",
       "2017-07-19 15:05:00+02:00  680.640000         28.0 -14422.100000  22.583333   \n",
       "2017-06-22 02:25:00+02:00    3.403067         28.0    -62.586207  22.566667   \n",
       "2017-07-16 13:45:00+02:00  885.935000         21.0 -12772.700000  22.716667   \n",
       "2017-07-15 03:50:00+02:00    3.090000         18.0    -13.233333  21.566667   \n",
       "2017-07-18 07:05:00+02:00   91.620000         19.0     -5.793103  22.566667   \n",
       "...                               ...          ...           ...        ...   \n",
       "2017-06-11 13:20:00+02:00  916.328067         22.5   2138.344828  23.100000   \n",
       "2017-07-19 16:05:00+02:00  450.750000         28.0 -14195.275862  22.833333   \n",
       "2017-07-15 20:30:00+02:00   95.620000         22.0  -6755.379310  23.066667   \n",
       "2017-06-22 04:05:00+02:00    3.310567         23.0    -42.000000  22.691667   \n",
       "2017-07-15 11:30:00+02:00  801.415000         21.0   2374.068966  21.350000   \n",
       "\n",
       "                                    u_1        y_1        y_2        y_3  \n",
       "timestamp                                                                 \n",
       "2017-07-19 15:05:00+02:00 -14336.689655  22.600000  22.733333  22.783333  \n",
       "2017-06-22 02:25:00+02:00    -90.517241  22.600000  22.650000  22.833333  \n",
       "2017-07-16 13:45:00+02:00 -13091.586207  22.866667  22.850000  22.633333  \n",
       "2017-07-15 03:50:00+02:00    -12.758621  21.516667  21.533333  21.558333  \n",
       "2017-07-18 07:05:00+02:00      6.517241  22.533333  22.566667  22.566667  \n",
       "...                                 ...        ...        ...        ...  \n",
       "2017-06-11 13:20:00+02:00 -15974.793103  23.200000  23.383333  23.583333  \n",
       "2017-07-19 16:05:00+02:00 -14086.500000  23.000000  23.033333  23.166667  \n",
       "2017-07-15 20:30:00+02:00     -2.793103  22.833333  22.833333  22.633333  \n",
       "2017-06-22 04:05:00+02:00    -65.600000  22.658333  22.583333  22.583333  \n",
       "2017-07-15 11:30:00+02:00 -12525.620690  21.350000  21.216667  21.250000  \n",
       "\n",
       "[150 rows x 8 columns]"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_sampled"
   ]
  }
 ],
 "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": "3.9.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}